no code implementations • ECCV 2020 • Jiayan Qiu, Yiding Yang, Xinchao Wang, DaCheng Tao
This seemingly minor difference in fact makes the HVITA a much challenging task, as the restoration algorithm would have to not only infer the category of the object in total absentia, but also hallucinate an object of which the appearance is consistent with the background.
1 code implementation • ACL 2022 • Liang Ding, Longyue Wang, Shuming Shi, DaCheng Tao, Zhaopeng Tu
In this work, we provide an appealing alternative for NAT – monolingual KD, which trains NAT student on external monolingual data with AT teacher trained on the original bilingual data.
no code implementations • ICML 2020 • Jiaxian Guo, Mingming Gong, Tongliang Liu, Kun Zhang, DaCheng Tao
Distribution shift is a major obstacle to the deployment of current deep learning models on real-world problems.
1 code implementation • ICML 2020 • Zhen Wang, Liu Liu, DaCheng Tao
In order to fill in these research gaps, we propose a novel deep neural network (DNN) based framework, Deep Streaming Label Learning (DSLL), to classify instances with newly emerged labels effectively.
no code implementations • ICML 2020 • Xiyu Yu, Tongliang Liu, Mingming Gong, Kun Zhang, Kayhan Batmanghelich, DaCheng Tao
Domain adaptation aims to correct the classifiers when faced with distribution shift between source (training) and target (test) domains.
no code implementations • ECCV 2020 • Xikun Zhang, Chang Xu, DaCheng Tao
Dropout has been widely adopted to regularize graph convolutional networks (GCNs) by randomly zeroing entries of the node feature vectors and obtains promising performance on various tasks.
1 code implementation • ECCV 2020 • Xubin Zhong, Changxing Ding, Xian Qu, DaCheng Tao
First, PD-Net augments human pose and spatial features for HOI detection using language priors, enabling the verb classifiers to receive language hints that reduce the intra-class variation of the same verb.
no code implementations • ACL (IWSLT) 2021 • Liang Ding, DaCheng Tao
Our constrained system is based on a pipeline framework, i. e. ASR and NMT.
no code implementations • 6 Jun 2024 • Zonghao Ying, Aishan Liu, Tianyuan Zhang, Zhengmin Yu, Siyuan Liang, Xianglong Liu, DaCheng Tao
To address this limitation, this paper introduces the Bi-Modal Adversarial Prompt Attack (BAP), which executes jailbreaks by optimizing textual and visual prompts cohesively.
no code implementations • 5 Jun 2024 • Anke Tang, Li Shen, Yong Luo, Han Hu, Bo Do, DaCheng Tao
These techniques range from model ensemble methods, which combine the predictions to improve the overall performance, to model merging, which integrates different models into a single one, and model mixing methods, which upscale or recombine the components of the original models.
no code implementations • 3 Jun 2024 • Tianyuan Zhang, Lu Wang, Hainan Li, Yisong Xiao, Siyuan Liang, Aishan Liu, Xianglong Liu, DaCheng Tao
For the first time, this paper studies the potential threats caused by these environmental illusions to LD and establishes the first comprehensive benchmark LanEvil for evaluating the robustness of LD against this natural corruption.
no code implementations • 30 May 2024 • Xiaofeng Cong, Yu Zhao, Jie Gui, JunMing Hou, DaCheng Tao
To promote future research, we summarize the UIE task from multiple perspectives.
1 code implementation • 28 May 2024 • Shengchao Hu, Ziqing Fan, Li Shen, Ya zhang, Yanfeng Wang, DaCheng Tao
However, variations in task content and complexity pose significant challenges in policy formulation, necessitating judicious parameter sharing and management of conflicting gradients for optimal policy performance.
1 code implementation • 27 May 2024 • Shengchao Hu, Ziqing Fan, Chaoqin Huang, Li Shen, Ya zhang, Yanfeng Wang, DaCheng Tao
Recent advancements in offline reinforcement learning (RL) have underscored the capabilities of Conditional Sequence Modeling (CSM), a paradigm that learns the action distribution based on history trajectory and target returns for each state.
no code implementations • 26 May 2024 • Yongxian Wei, Zixuan Hu, Li Shen, Zhenyi Wang, Yu Li, Chun Yuan, DaCheng Tao
Based on our findings, we propose Task Groupings Regularization, a novel approach that benefits from model heterogeneity by grouping and aligning conflicting tasks.
1 code implementation • 14 May 2024 • Shengchao Hu, Li Shen, Ya zhang, DaCheng Tao
In numerous artificial intelligence applications, the collaborative efforts of multiple intelligent agents are imperative for the successful attainment of target objectives.
no code implementations • 12 May 2024 • Xinbiao Wang, Yuxuan Du, Kecheng Liu, Yong Luo, Bo Du, DaCheng Tao
The No-Free-Lunch (NFL) theorem, which quantifies problem- and data-independent generalization errors regardless of the optimization process, provides a foundational framework for comprehending diverse learning protocols' potential.
1 code implementation • 9 May 2024 • Ruihao Gong, Yang Yong, Shiqiao Gu, Yushi Huang, Yunchen Zhang, Xianglong Liu, DaCheng Tao
Recent advancements in large language models (LLMs) are propelling us toward artificial general intelligence, thanks to their remarkable emergent abilities and reasoning capabilities.
no code implementations • 2 May 2024 • Tianle Xia, Liang Ding, Guojia Wan, Yibing Zhan, Bo Du, DaCheng Tao
Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition, to stimulate the reasoning capability of LLMs.
no code implementations • 2 May 2024 • Yongxian Wei, Zixuan Hu, Zhenyi Wang, Li Shen, Chun Yuan, DaCheng Tao
Data-Free Meta-Learning (DFML) aims to extract knowledge from a collection of pre-trained models without requiring the original data, presenting practical benefits in contexts constrained by data privacy concerns.
1 code implementation • 29 Apr 2024 • Xinyu Ma, Xuebo Liu, Derek F. Wong, Jun Rao, Bei Li, Liang Ding, Lidia S. Chao, DaCheng Tao, Min Zhang
Experimental results show that MMT models trained on our dataset exhibit a greater ability to exploit visual information than those trained on other MMT datasets.
no code implementations • 24 Apr 2024 • Xuming An, Dui Wang, Li Shen, Yong Luo, Han Hu, Bo Du, Yonggang Wen, DaCheng Tao
Specifically, FedALC estimates the label correlations in the class embedding learning for different label pairs and utilizes it to improve the model training.
1 code implementation • 23 Apr 2024 • Qihuang Zhong, Kang Wang, Ziyang Xu, Juhua Liu, Liang Ding, Bo Du, DaCheng Tao
To this end, we propose a simple-yet-effective method, namely Deeply Understanding the Problems (DUP), to improve the LLMs' math problem-solving ability by addressing semantic misunderstanding errors.
Ranked #1 on Math Word Problem Solving on SVAMP (Accuracy metric)
1 code implementation • 22 Apr 2024 • Zhengwei Tao, Ting-En Lin, Xiancai Chen, Hangyu Li, Yuchuan Wu, Yongbin Li, Zhi Jin, Fei Huang, DaCheng Tao, Jingren Zhou
To address this issue, self-evolution approaches that enable LLM to autonomously acquire, refine, and learn from experiences generated by the model itself are rapidly growing.
1 code implementation • 16 Apr 2024 • Jiangning Zhang, Chengjie Wang, Xiangtai Li, Guanzhong Tian, Zhucun Xue, Yong liu, Guansong Pang, DaCheng Tao
Moreover, current metrics such as AU-ROC have nearly reached saturation on simple datasets, which prevents a comprehensive evaluation of different methods.
no code implementations • 8 Apr 2024 • Haimei Zhao, Jing Zhang, Zhuo Chen, Shanshan Zhao, DaCheng Tao
We devote UniMix to two main setups: 1) unsupervised domain adaption, adapting the model from the clear weather source domain to the adverse weather target domain; 2) domain generalization, learning a model that generalizes well to unseen scenes in adverse weather.
1 code implementation • 26 Mar 2024 • Gan Pei, Jiangning Zhang, Menghan Hu, Zhenyu Zhang, Chengjie Wang, Yunsheng Wu, Guangtao Zhai, Jian Yang, Chunhua Shen, DaCheng Tao
Deepfake is a technology dedicated to creating highly realistic facial images and videos under specific conditions, which has significant application potential in fields such as entertainment, movie production, digital human creation, to name a few.
1 code implementation • 24 Mar 2024 • Siyuan Liang, Wei Wang, Ruoyu Chen, Aishan Liu, Boxi Wu, Ee-Chien Chang, Xiaochun Cao, DaCheng Tao
This paper aims to bridge this gap by conducting a comprehensive review and analysis of object detectors in open environments.
no code implementations • 23 Mar 2024 • Sihan Ma, Qiong Cao, Jing Zhang, DaCheng Tao
This paper addresses the problem of generating 3D interactive human motion from text.
1 code implementation • 21 Mar 2024 • Changtong Zan, Liang Ding, Li Shen, Yibing Zhen, Weifeng Liu, DaCheng Tao
In this work, we design a two-stage fine-tuning algorithm to improve the instruction-following ability (especially the translation direction) of LLMs.
2 code implementations • 21 Mar 2024 • Sanqing Qu, Tianpei Zou, Florian Röhrbein, Cewu Lu, Guang Chen, DaCheng Tao, Changjun Jiang
GLC++ enhances the novel category clustering accuracy of GLC by 4. 3% in open-set scenarios on Office-Home.
1 code implementation • 20 Mar 2024 • Di Wang, Jing Zhang, Minqiang Xu, Lin Liu, Dongsheng Wang, Erzhong Gao, Chengxi Han, HaoNan Guo, Bo Du, DaCheng Tao, Liangpei Zhang
However, transferring the pretrained models to downstream tasks may encounter task discrepancy due to their formulation of pretraining as image classification or object discrimination tasks.
Ranked #1 on Semantic Segmentation on SpaceNet 1 (using extra training data)
Aerial Scene Classification Building change detection for remote sensing images +13
1 code implementation • 17 Mar 2024 • Yiyang Chen, Lunhao Duan, Shanshan Zhao, Changxing Ding, DaCheng Tao
Equipped with LCRF and RPR, our LocoTrans is capable of learning local-consistent transformation and preserving local geometry, which benefits rotation invariance learning.
1 code implementation • 15 Mar 2024 • Ziyang Xu, Keqin Peng, Liang Ding, DaCheng Tao, Xiliang Lu
Experiments across various prompts, PLMs, and benchmarks show that our approach can not only correct the overfitted performance caused by prompt bias, but also significantly improve the prompt retrieval capability (up to 10% absolute performance gain).
no code implementations • 1 Mar 2024 • Wenjie Xuan, Yufei Xu, Shanshan Zhao, Chaoyue Wang, Juhua Liu, Bo Du, DaCheng Tao
Subsequently, to enhance controllability with inexplicit masks, an advanced Shape-aware ControlNet consisting of a deterioration estimator and a shape-prior modulation block is devised.
1 code implementation • 29 Feb 2024 • Jianbin Zheng, Minghui Hu, Zhongyi Fan, Chaoyue Wang, Changxing Ding, DaCheng Tao, Tat-Jen Cham
Consequently, we introduce Trajectory Consistency Distillation (TCD), which encompasses trajectory consistency function and strategic stochastic sampling.
no code implementations • 20 Feb 2024 • Zhiyao Ren, Yibing Zhan, Baosheng Yu, Liang Ding, DaCheng Tao
The copilot framework, which aims to enhance and tailor large language models (LLMs) for specific complex tasks without requiring fine-tuning, is gaining increasing attention from the community.
1 code implementation • 20 Feb 2024 • Xiaohan Xu, Ming Li, Chongyang Tao, Tao Shen, Reynold Cheng, Jinyang Li, Can Xu, DaCheng Tao, Tianyi Zhou
In the era of Large Language Models (LLMs), Knowledge Distillation (KD) emerges as a pivotal methodology for transferring advanced capabilities from leading proprietary LLMs, such as GPT-4, to their open-source counterparts like LLaMA and Mistral.
no code implementations • 19 Feb 2024 • Hong Chen, Chengtao Lv, Liang Ding, Haotong Qin, Xiabin Zhou, Yifu Ding, Xuebo Liu, Min Zhang, Jinyang Guo, Xianglong Liu, DaCheng Tao
Large language models (LLMs) have significantly advanced the field of natural language processing, while the expensive memory and computation consumption impede their practical deployment.
no code implementations • 19 Feb 2024 • Yifei Cheng, Li Shen, Linli Xu, Xun Qian, Shiwei Wu, Yiming Zhou, Tie Zhang, DaCheng Tao, Enhong Chen
However, existing compression methods either perform only unidirectional compression in one iteration with higher communication cost, or bidirectional compression with slower convergence rate.
no code implementations • 19 Feb 2024 • Qihuang Zhong, Liang Ding, Li Shen, Juhua Liu, Bo Du, DaCheng Tao
Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model.
no code implementations • 19 Feb 2024 • Qihuang Zhong, Liang Ding, Juhua Liu, Bo Du, DaCheng Tao
With the development of instruction-tuned large language models (LLMs), improving the safety of LLMs has become more critical.
no code implementations • 19 Feb 2024 • Shi Fu, Sen Zhang, Yingjie Wang, Xinmei Tian, DaCheng Tao
This paper tackles the emerging challenge of training generative models within a self-consuming loop, wherein successive generations of models are recursively trained on mixtures of real and synthetic data from previous generations.
1 code implementation • 18 Feb 2024 • Xikun Zhang, Dongjin Song, DaCheng Tao
To bridge the gap, we provide a comprehensive review of existing continual graph learning (CGL) algorithms by elucidating the different task settings and categorizing the existing methods based on their characteristics.
no code implementations • 14 Feb 2024 • Yuchun Miao, Sen Zhang, Liang Ding, Rong Bao, Lefei Zhang, DaCheng Tao
Inspired by this finding, we propose the Cluster Separation Index (CSI), which quantifies deviations in the IB latent space, as an indicator of reward overoptimization to facilitate the development of online mitigation strategies.
1 code implementation • 13 Feb 2024 • Ziyi Zhang, Sen Zhang, Yibing Zhan, Yong Luo, Yonggang Wen, DaCheng Tao
Then, we surprisingly discover that dormant neurons in our critic model act as a regularization against reward overoptimization while active neurons reflect primacy bias.
no code implementations • 6 Feb 2024 • Yanfang Zhang, Yiliu Sun, Yibing Zhan, Dapeng Tao, DaCheng Tao, Chen Gong
The experimental results on popular LLMs, such as GPT-3. 5-turbo and Gemini-pro, show that our IR method enhances the overall accuracy of factual reasoning by 27. 33% and mathematical proof by 31. 43%, when compared with traditional DR methods.
no code implementations • 5 Feb 2024 • Xiaoxing Wang, Jiaxing Li, Chao Xue, Wei Liu, Weifeng Liu, Xiaokang Yang, Junchi Yan, DaCheng Tao
BayesianOptimization(BO) is a sample-efficient black-box optimizer, and extensive methods have been proposed to build the absolute function response of the black-box function through a probabilistic surrogate model, including Tree-structured Parzen Estimator (TPE), random forest (SMAC), and Gaussian process (GP).
1 code implementation • 5 Feb 2024 • Enneng Yang, Li Shen, Zhenyi Wang, Guibing Guo, Xiaojun Chen, Xingwei Wang, DaCheng Tao
That is, there is a significant discrepancy in the representation distribution between the merged and individual models, resulting in poor performance of merged MTL.
no code implementations • 5 Feb 2024 • Yehui Tang, Yunhe Wang, Jianyuan Guo, Zhijun Tu, Kai Han, Hailin Hu, DaCheng Tao
Model compression methods reduce the memory and computational cost of Transformer, which is a necessary step to implement large language/vision models on practical devices.
1 code implementation • 4 Feb 2024 • Hao Wang, Licheng Pan, Zhichao Chen, Degui Yang, Sen Zhang, Yifei Yang, Xinggao Liu, Haoxuan Li, DaCheng Tao
Time series modeling is uniquely challenged by the presence of autocorrelation in both historical and label sequences.
no code implementations • 1 Feb 2024 • Anke Tang, Li Shen, Yong Luo, Nan Yin, Lefei Zhang, DaCheng Tao
A notable challenge is mitigating the interference between parameters of different models, which can substantially deteriorate performance.
1 code implementation • 31 Jan 2024 • Jingcai Guo, Zhijie Rao, Zhi Chen, Jingren Zhou, DaCheng Tao
To enrich the literature of this domain and provide a sound basis for its future development, in this paper, we present a broad review of recent advances for fine-grained analysis in ZSL.
1 code implementation • 31 Jan 2024 • Maoyuan Ye, Jing Zhang, Juhua Liu, Chenyu Liu, BaoCai Yin, Cong Liu, Bo Du, DaCheng Tao
In terms of the AMG mode, Hi-SAM segments text stroke foreground masks initially, then samples foreground points for hierarchical text mask generation and achieves layout analysis in passing.
Ranked #1 on Hierarchical Text Segmentation on HierText
no code implementations • 24 Jan 2024 • Xikun Zhang, Dongjin Song, Yixin Chen, DaCheng Tao
Memory replay based techniques have shown great success for continual learning with incrementally accumulated Euclidean data.
no code implementations • 23 Jan 2024 • Xin Lin, Chong Shi, Yibing Zhan, Zuopeng Yang, Yaqi Wu, DaCheng Tao
To address the above problems, in this paper, we introduce a network named TD$^2$-Net that aims at denoising and debiasing for dynamic SGG.
no code implementations • 22 Jan 2024 • Keqin Peng, Liang Ding, Yancheng Yuan, Xuebo Liu, Min Zhang, Yuanxin Ouyang, DaCheng Tao
In this work, we first revisit the factors contributing to this variance from both data and model aspects, and find that the choice of demonstration is both data- and model-dependent.
no code implementations • 16 Jan 2024 • Kaixin Huang, Li Shen, Chen Zhao, Chun Yuan, DaCheng Tao
We aim to investigate whether Decision Transformer (DT), another offline RL paradigm, can serve as a more suitable offline continuous learner to address these issues.
1 code implementation • 13 Jan 2024 • Haibin He, Maoyuan Ye, Jing Zhang, Juhua Liu, DaCheng Tao
In response to this issue, we propose to efficiently turn an off-the-shelf query-based image text spotter into a specialist on video and present a simple baseline termed GoMatching, which focuses the training efforts on tracking while maintaining strong recognition performance.
1 code implementation • 12 Jan 2024 • Shuai Wang, Liang Ding, Li Shen, Yong Luo, Bo Du, DaCheng Tao
Advancing automated programming necessitates robust and comprehensive code generation benchmarks, yet current evaluation frameworks largely neglect object-oriented programming (OOP) in favor of functional programming (FP), e. g., HumanEval and MBPP.
no code implementations • 12 Jan 2024 • Wenbin Wang, Liang Ding, Li Shen, Yong Luo, Han Hu, DaCheng Tao
Sentiment analysis is rapidly advancing by utilizing various data modalities (e. g., text, image).
1 code implementation • 12 Jan 2024 • Yuqi Zhang, Liang Ding, Lefei Zhang, DaCheng Tao
Aligning large language models (LLMs) with human values, particularly in the face of complex and stealthy jailbreak attacks, presents a formidable challenge.
no code implementations • 6 Jan 2024 • Tongyan Hua, Haotian Bai, Zidong Cao, Ming Liu, DaCheng Tao, Lin Wang
In this paper, we introduce Hi-Map, a novel monocular dense mapping approach based on Neural Radiance Field (NeRF).
no code implementations • 27 Dec 2023 • Yunhe Wang, Hanting Chen, Yehui Tang, Tianyu Guo, Kai Han, Ying Nie, Xutao Wang, Hailin Hu, Zheyuan Bai, Yun Wang, Fangcheng Liu, Zhicheng Liu, Jianyuan Guo, Sinan Zeng, Yinchen Zhang, Qinghua Xu, Qun Liu, Jun Yao, Chao Xu, DaCheng Tao
We then demonstrate that the proposed approach is significantly effective for enhancing the model nonlinearity through carefully designed ablations; thus, we present a new efficient model architecture for establishing modern, namely, PanGu-$\pi$.
no code implementations • 23 Dec 2023 • Aishan Liu, Xinwei Zhang, Yisong Xiao, Yuguang Zhou, Siyuan Liang, Jiakai Wang, Xianglong Liu, Xiaochun Cao, DaCheng Tao
This paper aims to raise awareness of the potential threats associated with applying PVMs in practical scenarios.
1 code implementation • NeurIPS 2023 • Lunhao Duan, Shanshan Zhao, Nan Xue, Mingming Gong, Gui-Song Xia, DaCheng Tao
Transformers have been recently explored for 3D point cloud understanding with impressive progress achieved.
Ranked #5 on Semantic Segmentation on S3DIS Area5
1 code implementation • 12 Dec 2023 • Jiangning Zhang, Xuhai Chen, Yabiao Wang, Chengjie Wang, Yong liu, Xiangtai Li, Ming-Hsuan Yang, DaCheng Tao
Following this spirit, this paper explores plain ViT architecture for MUAD.
1 code implementation • 11 Dec 2023 • Anke Tang, Li Shen, Yong Luo, Liang Ding, Han Hu, Bo Du, DaCheng Tao
At the upper level, we focus on learning a shared Concrete mask to identify the subspace, while at the inner level, model merging is performed to maximize the performance of the merged model.
1 code implementation • 4 Dec 2023 • Kaiwen Yang, Tao Shen, Xinmei Tian, Xiubo Geng, Chongyang Tao, DaCheng Tao, Tianyi Zhou
QVix enables a wider exploration of visual scenes, improving the LVLMs' reasoning accuracy and depth in tasks such as visual question answering and visual entailment.
no code implementations • 4 Dec 2023 • Xubin Zhong, Changxing Ding, Yupeng Hu, DaCheng Tao
In this paper, we improve the performance of one-stage methods by enabling them to extract disentangled interaction representations.
1 code implementation • 29 Nov 2023 • Wenquan Lu, Yufei Xu, Jing Zhang, Chaoyue Wang, DaCheng Tao
Given a generated failed image due to malformed hands, we utilize ControlNet modules to re-inject such correct hand information.
no code implementations • 27 Nov 2023 • Minghui Hu, Jianbin Zheng, Chuanxia Zheng, Chaoyue Wang, DaCheng Tao, Tat-Jen Cham
By integrating a compact network and incorporating an additional simple yet effective step during inference, OMS elevates image fidelity and harmonizes the dichotomy between training and inference, while preserving original model parameters.
no code implementations • 23 Nov 2023 • Zixuan Hu, Li Shen, Zhenyi Wang, Yongxian Wei, Baoyuan Wu, Chun Yuan, DaCheng Tao
TDS leads to a biased meta-learner because of the skewed task distribution towards newly generated tasks.
1 code implementation • 22 Nov 2023 • Zhe Zhang, Gaochang Wu, Jing Zhang, Chunhua Shen, DaCheng Tao, Tianyou Chai
To solve the challenge, we propose a novel DA-STC method for domain adaptive video semantic segmentation, which incorporates a bidirectional multi-level spatio-temporal fusion module and a category-aware spatio-temporal feature alignment module to facilitate consistent learning for domain-invariant features.
no code implementations • 13 Nov 2023 • Zeqiao Zhou, Yuxuan Du, Xu-Fei Yin, Shanshan Zhao, Xinmei Tian, DaCheng Tao
DQS incorporates two essential components: a Graph Neural Network (GNN) predictor and a trigonometric interpolation algorithm.
no code implementations • 7 Nov 2023 • Yang Qian, Yuxuan Du, Zhenliang He, Min-Hsiu Hsieh, DaCheng Tao
Cross-platform verification, a critical undertaking in the realm of early-stage quantum computing, endeavors to characterize the similarity of two imperfect quantum devices executing identical algorithms, utilizing minimal measurements.
no code implementations • 20 Oct 2023 • Miaoxi Zhu, Qihuang Zhong, Li Shen, Liang Ding, Juhua Liu, Bo Du, DaCheng Tao
The key algorithm in solving ZSAQ is the SAM-SGA optimization, which aims to improve the quantization accuracy and model generalization via optimizing a minimax problem.
no code implementations • 18 Oct 2023 • Liu Liu, Xuanqing Liu, Cho-Jui Hsieh, DaCheng Tao
In this paper, we explore a family of stochastic TR and ARC methods that can simultaneously provide inexact computations of the Hessian matrix, gradient, and function values.
1 code implementation • 15 Oct 2023 • Shwai He, Run-Ze Fan, Liang Ding, Li Shen, Tianyi Zhou, DaCheng Tao
Although a sparse Mixture of Experts (MoE) can reduce the cost by activating a small subset of parameters (e. g., one expert) for each input, its computation escalates significantly if increasing the number of activated experts, limiting its practical utility.
no code implementations • 15 Oct 2023 • Boan Liu, Liang Ding, Li Shen, Keqin Peng, Yu Cao, Dazhao Cheng, DaCheng Tao
The Mixture of Experts (MoE) has emerged as a highly successful technique in deep learning, based on the principle of divide-and-conquer to maximize model capacity without significant additional computational cost.
1 code implementation • 12 Oct 2023 • Hongling Zheng, Li Shen, Anke Tang, Yong Luo, Han Hu, Bo Du, DaCheng Tao
LFM focuses on the research, modification, and design of FM based on the model interface, so as to better understand the model structure and weights (in a black box environment), and to generalize the model to downstream tasks.
1 code implementation • 11 Oct 2023 • Guozheng Ma, Lu Li, Sen Zhang, Zixuan Liu, Zhen Wang, Yixin Chen, Li Shen, Xueqian Wang, DaCheng Tao
Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning (VRL).
1 code implementation • 11 Oct 2023 • Haibo Qiu, Baosheng Yu, Yixin Chen, DaCheng Tao
Significant progress has been made recently in point cloud segmentation utilizing an encoder-decoder framework, which initially encodes point clouds into low-resolution representations and subsequently decodes high-resolution predictions.
Ranked #5 on Semantic Segmentation on ScanNet
1 code implementation • 7 Oct 2023 • Anke Tang, Li Shen, Yong Luo, Yibing Zhan, Han Hu, Bo Du, Yixin Chen, DaCheng Tao
We demonstrate that our partial linearization technique enables a more effective fusion of multiple tasks into a single model, outperforming standard adapter tuning and task arithmetic alone.
no code implementations • 5 Oct 2023 • Yan Sun, Li Shen, DaCheng Tao
Both centralized and decentralized approaches have shown excellent performance and great application value in federated learning (FL).
no code implementations • 4 Oct 2023 • Zihao Lin, Yan Sun, Yifan Shi, Xueqian Wang, Lifu Huang, Li Shen, DaCheng Tao
With the blowout development of pre-trained models (PTMs), the efficient tuning of these models for diverse downstream applications has emerged as a pivotal research concern.
1 code implementation • 4 Oct 2023 • Enneng Yang, Zhenyi Wang, Li Shen, Shiwei Liu, Guibing Guo, Xingwei Wang, DaCheng Tao
This approach aims to autonomously learn the coefficients for model merging, either in a task-wise or layer-wise manner, without relying on the original training data.
1 code implementation • 29 Sep 2023 • Hao liu, Jiarui Feng, Lecheng Kong, Ningyue Liang, DaCheng Tao, Yixin Chen, Muhan Zhang
For in-context learning on graphs, OFA introduces a novel graph prompting paradigm that appends prompting substructures to the input graph, which enables it to address varied tasks without fine-tuning.
1 code implementation • 28 Sep 2023 • Changtong Zan, Liang Ding, Li Shen, Yibin Lei, Yibing Zhan, Weifeng Liu, DaCheng Tao
Zero-shot translation (ZST), which is generally based on a multilingual neural machine translation model, aims to translate between unseen language pairs in training data.
no code implementations • 22 Sep 2023 • Feng Yan, Xiaoheng Jiang, Yang Lu, Lisha Cui, Shupan Li, Jiale Cao, Mingliang Xu, DaCheng Tao
To this end, we develop a Global Context Aggregation Network (GCANet) for lightweight saliency detection of surface defects on the encoder-decoder structure.
no code implementations • 22 Sep 2023 • Xiaoheng Jiang, Kaiyi Guo, Yang Lu, Feng Yan, Hao liu, Jiale Cao, Mingliang Xu, DaCheng Tao
To address these issues, we propose a transformer network with multi-stage CNN (Convolutional Neural Network) feature injection for surface defect segmentation, which is a UNet-like structure named CINFormer.
1 code implementation • 20 Sep 2023 • Haoyu Wang, Guozheng Ma, Cong Yu, Ning Gui, Linrui Zhang, Zhiqi Huang, Suwei Ma, Yongzhe Chang, Sen Zhang, Li Shen, Xueqian Wang, Peilin Zhao, DaCheng Tao
Notably, we are surprised to discover that robustness tends to decrease as fine-tuning (SFT and RLHF) is conducted.
1 code implementation • 19 Sep 2023 • Hao liu, Jiarui Feng, Lecheng Kong, DaCheng Tao, Yixin Chen, Muhan Zhang
In our study, we first identify two crucial advantages of contrastive learning compared to meta learning, including (1) the comprehensive utilization of graph nodes and (2) the power of graph augmentations.
no code implementations • 18 Sep 2023 • Hao Sun, Li Shen, Shixiang Chen, Jingwei Sun, Jing Li, Guangzhong Sun, DaCheng Tao
Federated learning is an emerging distributed machine learning method, enables a large number of clients to train a model without exchanging their local data.
3 code implementations • 11 Sep 2023 • Dingfeng Shi, Qiong Cao, Yujie Zhong, Shan An, Jian Cheng, Haogang Zhu, DaCheng Tao
Temporal action detection (TAD) aims to detect all action boundaries and their corresponding categories in an untrimmed video.
Ranked #1 on Temporal Action Localization on MultiTHUMOS
no code implementations • 2 Sep 2023 • Fengxiang Bie, Yibo Yang, Zhongzhu Zhou, Adam Ghanem, Minjia Zhang, Zhewei Yao, Xiaoxia Wu, Connor Holmes, Pareesa Golnari, David A. Clifton, Yuxiong He, DaCheng Tao, Shuaiwen Leon Song
Text-to-image generation (TTI) refers to the usage of models that could process text input and generate high fidelity images based on text descriptions.
1 code implementation • 1 Sep 2023 • Shengcong Chen, Changxing Ding, DaCheng Tao, Hao Chen
Second, we propose a new instance normalization method that is robust to the variation in foreground-background ratios.
no code implementations • 31 Aug 2023 • Enneng Yang, Zhenyi Wang, Li Shen, Nan Yin, Tongliang Liu, Guibing Guo, Xingwei Wang, DaCheng Tao
Next, we train the CL model by minimizing the gap between the responses of the CL model and the black-box API on synthetic data, to transfer the API's knowledge to the CL model.
1 code implementation • 31 Aug 2023 • Zehao Dong, Weidong Cao, Muhan Zhang, DaCheng Tao, Yixin Chen, Xuan Zhang
The electronic design automation of analog circuits has been a longstanding challenge in the integrated circuit field due to the huge design space and complex design trade-offs among circuit specifications.
no code implementations • 30 Aug 2023 • Shwai He, Run-Ze Fan, Liang Ding, Li Shen, Tianyi Zhou, DaCheng Tao
Adapter tuning, which updates only a few parameters, has become a mainstream method for fine-tuning pretrained language models to downstream tasks.
no code implementations • 29 Aug 2023 • Qingyue Wang, Liang Ding, Yanan Cao, Zhiliang Tian, Shi Wang, DaCheng Tao, Li Guo
We evaluate our method on both open and closed LLMs, and the experiments on the widely-used public dataset show that our method can generate more consistent responses in a long-context conversation.
no code implementations • 22 Aug 2023 • Yuxuan Du, Yibo Yang, Tongliang Liu, Zhouchen Lin, Bernard Ghanem, DaCheng Tao
Understanding the dynamics of large quantum systems is hindered by the curse of dimensionality.
no code implementations • 18 Aug 2023 • Xiaoge Deng, Li Shen, Shengwei Li, Tao Sun, Dongsheng Li, DaCheng Tao
Stochastic gradient descent (SGD) performed in an asynchronous manner plays a crucial role in training large-scale machine learning models.
no code implementations • 16 Aug 2023 • Qinglun Li, Li Shen, Guanghao Li, Quanjun Yin, DaCheng Tao
To address the communication burden issues associated with federated learning (FL), decentralized federated learning (DFL) discards the central server and establishes a decentralized communication network, where each client communicates only with neighboring clients.
1 code implementation • 10 Aug 2023 • Yangyang Xu, Yibo Yang, Bernard Ghanem, Lefei Zhang, Du Bo, DaCheng Tao
In this work, we present a novel MTL model by combining both merits of deformable CNN and query-based Transformer with shared gating for multi-task learning of dense prediction.
no code implementations • 5 Aug 2023 • Yiyang Chen, Shanshan Zhao, Changxing Ding, Liyao Tang, Chaoyue Wang, DaCheng Tao
In recent years, cross-modal domain adaptation has been studied on the paired 2D image and 3D LiDAR data to ease the labeling costs for 3D LiDAR semantic segmentation (3DLSS) in the target domain.
2 code implementations • 3 Aug 2023 • Yibo Yang, Haobo Yuan, Xiangtai Li, Jianlong Wu, Lefei Zhang, Zhouchen Lin, Philip Torr, DaCheng Tao, Bernard Ghanem
Beyond the normal case, long-tail class incremental learning and few-shot class incremental learning are also proposed to consider the data imbalance and data scarcity, respectively, which are common in real-world implementations and further exacerbate the well-known problem of catastrophic forgetting.
no code implementations • 30 Jul 2023 • Yan Sun, Li Shen, Hao Sun, Liang Ding, DaCheng Tao
Adaptive optimization has achieved notable success for distributed learning while extending adaptive optimizer to federated Learning (FL) suffers from severe inefficiency, including (i) rugged convergence due to inaccurate gradient estimation in global adaptive optimizer; (ii) client drifts exacerbated by local over-fitting with the local adaptive optimizer.
no code implementations • 26 Jul 2023 • Chao Zhang, Xinyu Chen, Wensheng Li, Lixue Liu, Wei Wu, DaCheng Tao
In this paper, we measure the linear separability of hidden layer outputs to study the characteristics of deep neural networks.
1 code implementation • 26 Jul 2023 • Wenjie Xuan, Shanshan Zhao, Yu Yao, Juhua Liu, Tongliang Liu, Yixin Chen, Bo Du, DaCheng Tao
Exploiting the estimated noise transitions, our model, named PNT-Edge, is able to fit the prediction to clean labels.
1 code implementation • 22 Jul 2023 • Cheng Wen, Baosheng Yu, Rao Fu, DaCheng Tao
A generative model for high-fidelity point clouds is of great importance in synthesizing 3d environments for applications such as autonomous driving and robotics.
2 code implementations • 20 Jul 2023 • Mang Ye, Xiuwen Fang, Bo Du, Pong C. Yuen, DaCheng Tao
Therefore, a systematic survey on this topic about the research challenges and state-of-the-art is essential.
1 code implementation • 17 Jul 2023 • Shiye Lei, Hao Chen, Sen Zhang, Bo Zhao, DaCheng Tao
With the rapid development of Artificial Intelligence Generated Content (AIGC), it has become common practice in many learning tasks to train or fine-tune large models on synthetic data due to the data-scarcity and privacy leakage problems.
1 code implementation • 30 Jun 2023 • Peng Mi, Li Shen, Tianhe Ren, Yiyi Zhou, Tianshuo Xu, Xiaoshuai Sun, Tongliang Liu, Rongrong Ji, DaCheng Tao
Sharpness-Aware Minimization (SAM) is a popular solution that smooths the loss landscape by minimizing the maximized change of training loss when adding a perturbation to the weight.
1 code implementation • 29 Jun 2023 • Sihan Ma, Qiong Cao, Hongwei Yi, Jing Zhang, DaCheng Tao
Demystifying complex human-ground interactions is essential for accurate and realistic 3D human motion reconstruction from RGB videos, as it ensures consistency between the humans and the ground plane.
1 code implementation • 28 Jun 2023 • Jianzong Wu, Xiangtai Li, Shilin Xu, Haobo Yuan, Henghui Ding, Yibo Yang, Xia Li, Jiangning Zhang, Yunhai Tong, Xudong Jiang, Bernard Ghanem, DaCheng Tao
To our knowledge, this is the first comprehensive literature review of open vocabulary learning.
1 code implementation • 19 Jun 2023 • Ting Zhe, YongQian Li, Jing Zhang, Yong Luo, Han Hu, Bo Du, Yonggang Wen, DaCheng Tao
We represent the action information in each hand interaction region as a triplet, resulting in a total of 878 action triplets.
1 code implementation • 16 Jun 2023 • Shuangtong Li, Tianyi Zhou, Xinmei Tian, DaCheng Tao
We propose "Structured Cooperative Learning (SCooL)", in which a cooperation graph across devices is generated by a graphical model prior to automatically coordinate mutual learning between devices.
no code implementations • 8 Jun 2023 • Jifeng Hu, Yanchao Sun, Sili Huang, Siyuan Guo, Hechang Chen, Li Shen, Lichao Sun, Yi Chang, DaCheng Tao
Recent works have shown the potential of diffusion models in computer vision and natural language processing.
2 code implementations • International Journal of Computer Vision 2023 • Shengping Zhang, Xianzhu Liu, Haozhe Xie, Liqiang Nie, Huiyu Zhou, DaCheng Tao, Xuelong Li
It exploits the repetitive geometric structures in common 3D objects to recover the complete shapes, which contains three sub-networks: geometric patch network, structure transformation network, and detail refinement network.
Ranked #4 on Point Cloud Completion on ShapeNet
1 code implementation • 6 Jun 2023 • Fusheng Hao, Fengxiang He, Yikai Wang, Fuxiang Wu, Jing Zhang, Jun Cheng, DaCheng Tao
Massive human-related data is collected to train neural networks for computer vision tasks.
1 code implementation • 6 Jun 2023 • Xinbiao Wang, Yuxuan Du, Zhuozhuo Tu, Yong Luo, Xiao Yuan, DaCheng Tao
Recent progress has highlighted its positive impact on learning quantum dynamics, wherein the integration of entanglement into quantum operations or measurements of quantum machine learning (QML) models leads to substantial reductions in training data size, surpassing a specified prediction error threshold.
1 code implementation • NeurIPS 2023 • Jiarui Feng, Lecheng Kong, Hao liu, DaCheng Tao, Fuhai Li, Muhan Zhang, Yixin Chen
We theoretically prove that even if we fix the space complexity to $O(n^k)$ (for any $k\geq 2$) in $(k, t)$-FWL, we can construct an expressiveness hierarchy up to solving the graph isomorphism problem.
Ranked #2 on Graph Regression on ZINC
no code implementations • 5 Jun 2023 • Changcheng Xiao, Qiong Cao, Yujie Zhong, Long Lan, Xiang Zhang, Zhigang Luo, DaCheng Tao
This challenge arises from two main factors: the insufficient discriminability of ReID features and the predominant utilization of linear motion models in MOT.
Ranked #4 on Multi-Object Tracking on SportsMOT
1 code implementation • 5 Jun 2023 • Tongtian Zhu, Fengxiang He, KaiXuan Chen, Mingli Song, DaCheng Tao
Decentralized stochastic gradient descent (D-SGD) allows collaborative learning on massive devices simultaneously without the control of a central server.
1 code implementation • 5 Jun 2023 • Yibin Lei, Liang Ding, Yu Cao, Changtong Zan, Andrew Yates, DaCheng Tao
Dense retrievers have achieved impressive performance, but their demand for abundant training data limits their application scenarios.
1 code implementation • 2 Jun 2023 • Haibo Qiu, Baosheng Yu, DaCheng Tao
In this paper, we propose a new transformer network equipped with a collect-and-distribute mechanism to communicate short- and long-range contexts of point clouds, which we refer to as CDFormer.
no code implementations • 1 Jun 2023 • Minghui Hu, Jianbin Zheng, Daqing Liu, Chuanxia Zheng, Chaoyue Wang, DaCheng Tao, Tat-Jen Cham
In this work, we propose Cocktail, a pipeline to mix various modalities into one embedding, amalgamated with a generalized ControlNet (gControlNet), a controllable normalisation (ControlNorm), and a spatial guidance sampling method, to actualize multi-modal and spatially-refined control for text-conditional diffusion models.
no code implementations • 1 Jun 2023 • Qingyue Wang, Liang Ding, Yanan Cao, Yibing Zhan, Zheng Lin, Shi Wang, DaCheng Tao, Li Guo
Zero-shot transfer learning for Dialogue State Tracking (DST) helps to handle a variety of task-oriented dialogue domains without the cost of collecting in-domain data.
1 code implementation • 31 May 2023 • Maoyuan Ye, Jing Zhang, Shanshan Zhao, Juhua Liu, Tongliang Liu, Bo Du, DaCheng Tao
In this paper, we present DeepSolo++, a simple DETR-like baseline that lets a single decoder with explicit points solo for text detection, recognition, and script identification simultaneously.
Ranked #1 on Text Spotting on Inverse-Text
1 code implementation • 28 May 2023 • Zixuan Hu, Li Shen, Zhenyi Wang, Baoyuan Wu, Chun Yuan, DaCheng Tao
Data-free meta-learning (DFML) aims to enable efficient learning of new tasks by meta-learning from a collection of pre-trained models without access to the training data.
1 code implementation • NeurIPS 2023 • Liyao Tang, Zhe Chen, Shanshan Zhao, Chaoyue Wang, DaCheng Tao
We hypothesize that this selective usage arises from the noise in pseudo-labels generated on unlabeled data.
no code implementations • 24 May 2023 • Yifan Shi, Yingqi Liu, Yan Sun, Zihao Lin, Li Shen, Xueqian Wang, DaCheng Tao
Personalized federated learning (PFL) aims to produce the greatest personalized model for each client to face an insurmountable problem--data heterogeneity in real FL systems.
1 code implementation • 24 May 2023 • Qihuang Zhong, Liang Ding, Juhua Liu, Xuebo Liu, Min Zhang, Bo Du, DaCheng Tao
Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT, by skipping the computation of a subset of the input tokens at several middle layers.
1 code implementation • 24 May 2023 • Qihuang Zhong, Liang Ding, Juhua Liu, Bo Du, DaCheng Tao
Masked language modeling, widely used in discriminative language model (e. g., BERT) pretraining, commonly adopts a random masking strategy.
1 code implementation • 23 May 2023 • Anke Tang, Yong Luo, Han Hu, Fengxiang He, Kehua Su, Bo Du, Yixin Chen, DaCheng Tao
This paper studies multiparty learning, aiming to learn a model using the private data of different participants.
no code implementations • 22 May 2023 • Haoqi Zheng, Qihuang Zhong, Liang Ding, Zhiliang Tian, Xin Niu, Dongsheng Li, DaCheng Tao
However, most of the mixup methods do not consider the varying degree of learning difficulty in different stages of training and generate new samples with one hot labels, resulting in the model over confidence.
4 code implementations • NeurIPS 2023 • Hanting Chen, Yunhe Wang, Jianyuan Guo, DaCheng Tao
In this study, we introduce VanillaNet, a neural network architecture that embraces elegance in design.
1 code implementation • 19 May 2023 • Yan Sun, Li Shen, Shixiang Chen, Liang Ding, DaCheng Tao
In federated learning (FL), a cluster of local clients are chaired under the coordination of the global server and cooperatively train one model with privacy protection.
no code implementations • 16 May 2023 • Shengchao Hu, Li Shen, Ya zhang, DaCheng Tao
Our work contributes to the advancement of prompt-tuning approaches in RL, providing a promising direction for optimizing large RL agents for specific preference tasks.
no code implementations • 10 May 2023 • Jianbin Zheng, Daqing Liu, Chaoyue Wang, Minghui Hu, Zuopeng Yang, Changxing Ding, DaCheng Tao
To this end, we propose to generate images conditioned on the compositions of multimodal control signals, where modalities are imperfectly complementary, i. e., composed multimodal conditional image synthesis (CMCIS).
2 code implementations • NeurIPS 2023 • Di Wang, Jing Zhang, Bo Du, Minqiang Xu, Lin Liu, DaCheng Tao, Liangpei Zhang
In this study, we leverage SAM and existing RS object detection datasets to develop an efficient pipeline for generating a large-scale RS segmentation dataset, dubbed SAMRS.
no code implementations • 3 May 2023 • Tao Chen, Liang Lv, Di Wang, Jing Zhang, Yue Yang, Zeyang Zhao, Chen Wang, Xiaowei Guo, Hao Chen, Qingye Wang, Yufei Xu, Qiming Zhang, Bo Du, Liangpei Zhang, DaCheng Tao
With the world population rapidly increasing, transforming our agrifood systems to be more productive, efficient, safe, and sustainable is crucial to mitigate potential food shortages.
1 code implementation • 2 May 2023 • Haibin He, Jing Zhang, Mengyang Xu, Juhua Liu, Bo Du, DaCheng Tao
Video text spotting refers to localizing, recognizing, and tracking textual elements such as captions, logos, license plates, signs, and other forms of text within consecutive video frames.
1 code implementation • 1 May 2023 • Yifan Shi, Kang Wei, Li Shen, Yingqi Liu, Xueqian Wang, Bo Yuan, DaCheng Tao
To defend the inference attacks and mitigate the sensitive information leakages in Federated Learning (FL), client-level Differentially Private FL (DPFL) is the de-facto standard for privacy protection by clipping local updates and adding random noise.
no code implementations • CVPR 2023 • Yongcheng Jing, Chongbin Yuan, Li Ju, Yiding Yang, Xinchao Wang, DaCheng Tao
In this paper, we explore a novel model reusing task tailored for graph neural networks (GNNs), termed as "deep graph reprogramming".
no code implementations • 27 Apr 2023 • Zhi Hou, Baosheng Yu, DaCheng Tao
Human-object interactions (HOIs) are crucial for human-centric scene understanding applications such as human-centric visual generation, AR/VR, and robotics.
no code implementations • 23 Apr 2023 • Yongcheng Jing, Xinchao Wang, DaCheng Tao
The recent work known as Segment Anything (SA) has made significant strides in pushing the boundaries of semantic segmentation into the era of foundation models.
1 code implementation • 23 Apr 2023 • Di Wang, Bo Du, Liangpei Zhang, DaCheng Tao
Recent neural architecture search (NAS) based approaches have made great progress in hyperspectral image (HSI) classification tasks.
2 code implementations • 19 Apr 2023 • Di Wang, Jing Zhang, Bo Du, Liangpei Zhang, DaCheng Tao
Hyperspectral image (HSI) classification is challenging due to spatial variability caused by complex imaging conditions.
1 code implementation • 19 Apr 2023 • Kunping Huang, Sen Zhang, Jing Zhang, DaCheng Tao
This paper presents a timely and comprehensive review of event-based vSLAM algorithms that exploit the benefits of asynchronous and irregular event streams for localization and mapping tasks.
no code implementations • 14 Apr 2023 • Jinlong Fan, Jing Zhang, DaCheng Tao
Experiments on multiple human avatars demonstrate that our UVA achieves competitive results in novel view synthesis and novel pose rendering while enabling local and independent editing of geometry and appearance.
1 code implementation • 10 Apr 2023 • Jizhizi Li, Jing Zhang, DaCheng Tao
Image matting refers to extracting precise alpha matte from natural images, and it plays a critical role in various downstream applications, such as image editing.
no code implementations • 7 Apr 2023 • Li Shen, Yan Sun, Zhiyuan Yu, Liang Ding, Xinmei Tian, DaCheng Tao
The field of deep learning has witnessed significant progress, particularly in computer vision (CV), natural language processing (NLP), and speech.
no code implementations • 4 Apr 2023 • Zhihao Cheng, Kaining Zhang, Li Shen, DaCheng Tao
Despite remarkable successes in solving various complex decision-making tasks, training an imitation learning (IL) algorithm with deep neural networks (DNNs) suffers from the high computation burden.
1 code implementation • 3 Apr 2023 • Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou, DaCheng Tao, Xuelong Li
This weak projection, however, can be addressed by a Riemannian metric, and we show that geodesics computation and accurate interpolations between data samples on the Riemannian manifold can substantially improve the performance of deep generative models.
2 code implementations • 29 Mar 2023 • Haimei Zhao, Qiming Zhang, Shanshan Zhao, Zhe Chen, Jing Zhang, DaCheng Tao
Multi-view camera-based 3D object detection has become popular due to its low cost, but accurately inferring 3D geometry solely from camera data remains challenging and may lead to inferior performance.
1 code implementation • 27 Mar 2023 • Qiming Zhang, Jing Zhang, Yufei Xu, DaCheng Tao
Window-based attention has become a popular choice in vision transformers due to its superior performance, lower computational complexity, and less memory footprint.
1 code implementation • 24 Mar 2023 • Keqin Peng, Liang Ding, Qihuang Zhong, Li Shen, Xuebo Liu, Min Zhang, Yuanxin Ouyang, DaCheng Tao
We show that: 1) The performance of ChatGPT depends largely on temperature, and a lower temperature usually can achieve better performance; 2) Emphasizing the task information can further improve ChatGPT's performance, particularly in complex MT tasks; 3) Introducing domain information can elicit ChatGPT's generalization ability and improve its performance in the specific domain; 4) ChatGPT tends to generate hallucinations for non-English-centric MT tasks, which can be partially addressed by our proposed prompts but still need to be highlighted for the MT/NLP community.
1 code implementation • 24 Mar 2023 • Qingyu Lu, Baopu Qiu, Liang Ding, Kanjian Zhang, Tom Kocmi, DaCheng Tao
To further improve the performance of LLMs on MT quality assessment, we investigate several prompting designs, and propose a new prompting method called \textbf{\texttt{Error Analysis Prompting}} (EAPrompt) by combining Chain-of-Thoughts (Wei et al., 2022) and Error Analysis (Lu et al., 2023).
1 code implementation • CVPR 2023 • Yifan Shi, Yingqi Liu, Kang Wei, Li Shen, Xueqian Wang, DaCheng Tao
Specifically, DP-FedSAM integrates Sharpness Aware Minimization (SAM) optimizer to generate local flatness models with better stability and weight perturbation robustness, which results in the small norm of local updates and robustness to DP noise, thereby improving the performance.
1 code implementation • CVPR 2023 • Zixuan Hu, Li Shen, Zhenyi Wang, Tongliang Liu, Chun Yuan, DaCheng Tao
The goal of data-free meta-learning is to learn useful prior knowledge from a collection of pre-trained models without accessing their training data.
1 code implementation • 19 Mar 2023 • Kang Liao, Lang Nie, Shujuan Huang, Chunyu Lin, Jing Zhang, Yao Zhao, Moncef Gabbouj, DaCheng Tao
In this paper, we provide a comprehensive survey of learning-based camera calibration techniques, by analyzing their strengths and limitations.
no code implementations • 15 Mar 2023 • Guanghao Li, Wansen Wu, Yan Sun, Li Shen, Baoyuan Wu, DaCheng Tao
Then, the local model is trained on the input composed of raw data and a visual prompt to learn the distribution information contained in the prompt.
1 code implementation • ICCV 2023 • Haoyu He, Jianfei Cai, Jing Zhang, DaCheng Tao, Bohan Zhuang
Visual Parameter-Efficient Fine-Tuning (PEFT) has become a powerful alternative for full fine-tuning so as to adapt pre-trained vision models to downstream tasks, which only tunes a small number of parameters while freezing the vast majority ones to ease storage burden and optimization difficulty.
1 code implementation • CVPR 2023 • Dingfeng Shi, Yujie Zhong, Qiong Cao, Lin Ma, Jia Li, DaCheng Tao
In this paper, we present a one-stage framework TriDet for temporal action detection.
Ranked #2 on Temporal Action Localization on EPIC-KITCHENS-100
3 code implementations • CVPR 2023 • Sanqing Qu, Tianpei Zou, Florian Roehrbein, Cewu Lu, Guang Chen, DaCheng Tao, Changjun Jiang
We examine the superiority of our GLC on multiple benchmarks with different category shift scenarios, including partial-set, open-set, and open-partial-set DA.
Ranked #2 on Universal Domain Adaptation on VisDA2017
no code implementations • ICCV 2023 • Yuchun Miao, Lefei Zhang, Liangpei Zhang, DaCheng Tao
This is especially inappropriate for data-starved hyperspectral image (HSI) restoration.
no code implementations • 8 Mar 2023 • Xin Yan, Zuchao Li, Lefei Zhang, Bo Du, DaCheng Tao
Our proposed approach, \textbf{CCViT}, leverages k-means clustering to obtain centroids for image modeling without supervised training of tokenizer model.
no code implementations • 7 Mar 2023 • Shengchao Hu, Li Shen, Ya zhang, DaCheng Tao
Offline reinforcement learning (RL) is a challenging task, whose objective is to learn policies from static trajectory data without interacting with the environment.
no code implementations • 5 Mar 2023 • Hao liu, Muhan Zhang, Zehao Dong, Lecheng Kong, Yixin Chen, Bradley Fritz, DaCheng Tao, Christopher King
We view time-associated disease prediction as classification tasks at multiple time points.
1 code implementation • 2 Mar 2023 • Qi Zheng, Daqing Liu, Chaoyue Wang, Jing Zhang, Dadong Wang, DaCheng Tao
Vision-and-language navigation (VLN) simulates a visual agent that follows natural-language navigation instructions in real-world scenes.
no code implementations • 1 Mar 2023 • Chao Xue, Wei Liu, Shuai Xie, Zhenfang Wang, Jiaxing Li, Xuyang Peng, Liang Ding, Shanshan Zhao, Qiong Cao, Yibo Yang, Fengxiang He, Bohua Cai, Rongcheng Bian, Yiyan Zhao, Heliang Zheng, Xiangyang Liu, Dongkai Liu, Daqing Liu, Li Shen, Chang Li, Shijin Zhang, Yukang Zhang, Guanpu Chen, Shixiang Chen, Yibing Zhan, Jing Zhang, Chaoyue Wang, DaCheng Tao
Automated machine learning (AutoML) seeks to build ML models with minimal human effort.
no code implementations • 1 Mar 2023 • Hao Sun, Li Shen, Qihuang Zhong, Liang Ding, Shixiang Chen, Jingwei Sun, Jing Li, Guangzhong Sun, DaCheng Tao
Integrating SAM with adaptive learning rate and momentum acceleration, dubbed AdaSAM, has already been explored empirically to train large-scale deep neural networks without theoretical guarantee due to the triple difficulties in analyzing the coupled perturbation step, adaptive learning rate and momentum step.
no code implementations • 24 Feb 2023 • Guanghao Li, Li Shen, Yan Sun, Yue Hu, Han Hu, DaCheng Tao
Federated learning (FL) enables multiple clients to train a machine learning model collaboratively without exchanging their local data.
1 code implementation • 22 Feb 2023 • Junjie Yang, Tianlong Chen, Mingkang Zhu, Fengxiang He, DaCheng Tao, Yingbin Liang, Zhangyang Wang
While the optimizer generalization has been recently studied, the optimizee generalization (or learning to generalize) has not been rigorously studied in the L2O context, which is the aim of this paper.
1 code implementation • 21 Feb 2023 • Tiansheng Huang, Li Shen, Yan Sun, Weiwei Lin, DaCheng Tao
Personalized federated learning, as a variant of federated learning, trains customized models for clients using their heterogeneously distributed data.
1 code implementation • 21 Feb 2023 • Yan Sun, Li Shen, Tiansheng Huang, Liang Ding, DaCheng Tao
Federated learning is an emerging distributed machine learning framework which jointly trains a global model via a large number of local devices with data privacy protections.
1 code implementation • 19 Feb 2023 • Qihuang Zhong, Liang Ding, Juhua Liu, Bo Du, DaCheng Tao
Recently, ChatGPT has attracted great attention, as it can generate fluent and high-quality responses to human inquiries.
1 code implementation • 19 Feb 2023 • Aishan Liu, Jun Guo, Jiakai Wang, Siyuan Liang, Renshuai Tao, Wenbo Zhou, Cong Liu, Xianglong Liu, DaCheng Tao
In this paper, we take the first step toward the study of adversarial attacks targeted at X-ray prohibited item detection, and reveal the serious threats posed by such attacks in this safety-critical scenario.
no code implementations • 19 Feb 2023 • Weigang Lu, Ziyu Guan, Wei Zhao, Yaming Yang, Yuanhai Lv, Lining Xing, Baosheng Yu, DaCheng Tao
Pseudo Labeling is a technique used to improve the performance of semi-supervised Graph Neural Networks (GNNs) by generating additional pseudo-labels based on confident predictions.
no code implementations • 18 Feb 2023 • Qihuang Zhong, Liang Ding, Keqin Peng, Juhua Liu, Bo Du, Li Shen, Yibing Zhan, DaCheng Tao
This technical report briefly describes our JDExplore d-team's submission Vega v1 on the General Language Understanding Evaluation (GLUE) leaderboard, where GLUE is a collection of nine natural language understanding tasks, including question answering, linguistic acceptability, sentiment analysis, text similarity, paraphrase detection, and natural language inference.
1 code implementation • 17 Feb 2023 • Xu Zheng, Yexin Liu, Yunfan Lu, Tongyan Hua, Tianbo Pan, Weiming Zhang, DaCheng Tao, Lin Wang
Event cameras are bio-inspired sensors that capture the per-pixel intensity changes asynchronously and produce event streams encoding the time, pixel position, and polarity (sign) of the intensity changes.
no code implementations • 15 Feb 2023 • Dui Wang, Li Shen, Yong Luo, Han Hu, Kehua Su, Yonggang Wen, DaCheng Tao
In particular, we adopt the ``one-vs-all'' training strategy in each client to alleviate the unfair competition between classes by constructing a personalized binary classification problem for each class.
no code implementations • 11 Feb 2023 • Yixing Liu, Yan Sun, Zhengtao Ding, Li Shen, Bo Liu, DaCheng Tao
Federated learning (FL), as a collaborative distributed training paradigm with several edge computing devices under the coordination of a centralized server, is plagued by inconsistent local stationary points due to the heterogeneity of the local partial participation clients, which precipitates the local client-drifts problems and sparks off the unstable and slow convergence, especially on the aggravated heterogeneous dataset.
no code implementations • 10 Feb 2023 • Cheng Wen, Jianzhi Long, Baosheng Yu, DaCheng Tao
In this paper, we introduce a new method, PointWavelet, to explore local graphs in the spectral domain via a learnable graph wavelet transform.
no code implementations • 8 Feb 2023 • Yifan Shi, Li Shen, Kang Wei, Yan Sun, Bo Yuan, Xueqian Wang, DaCheng Tao
To mitigate the privacy leakages and communication burdens of Federated Learning (FL), decentralized FL (DFL) discards the central server and each client only communicates with its neighbors in a decentralized communication network.
no code implementations • 7 Feb 2023 • Jinlong Fan, Jing Zhang, Zhi Hou, DaCheng Tao
In this paper, we propose AniPixel, a novel animatable and generalizable human avatar reconstruction method that leverages pixel-aligned features for body geometry prediction and RGB color blending.
1 code implementation • 6 Feb 2023 • Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin, Philip Torr, DaCheng Tao
In this paper, we deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse, which reveals that the last-layer features of the same class will collapse into a vertex, and the vertices of all classes are aligned with the classifier prototypes, which are formed as a simplex equiangular tight frame (ETF).
1 code implementation • ICLR 2023 • Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin, Philip Torr, DaCheng Tao
In this paper, we deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse, which reveals that the last-layer features of the same class will collapse into a vertex, and the vertices of all classes are aligned with the classifier prototypes, which are formed as a simplex equiangular tight frame (ETF).
Ranked #3 on Few-Shot Class-Incremental Learning on CUB-200-2011
no code implementations • 28 Jan 2023 • Qin Zhang, Linrui Zhang, Haoran Xu, Li Shen, Bowen Wang, Yongzhe Chang, Xueqian Wang, Bo Yuan, DaCheng Tao
Offline safe RL is of great practical relevance for deploying agents in real-world applications.
no code implementations • 19 Jan 2023 • Guanpu Chen, Gehui Xu, Fengxiang He, Yiguang Hong, Leszek Rutkowski, DaCheng Tao
This paper takes conjugate transformation to the formulation of non-convex multi-player games, and casts the complementary problem into a variational inequality (VI) problem with a continuous pseudo-gradient mapping.
1 code implementation • 13 Jan 2023 • Shiye Lei, DaCheng Tao
Dataset distillation, a dataset reduction method, addresses this problem by synthesizing a small typical dataset from substantial data and has attracted much attention from the deep learning community.
1 code implementation • 13 Jan 2023 • Jie Gui, Tuo Chen, Jing Zhang, Qiong Cao, Zhenan Sun, Hao Luo, DaCheng Tao
Deep supervised learning algorithms typically require a large volume of labeled data to achieve satisfactory performance.
1 code implementation • 3 Jan 2023 • Xiangtai Li, Shilin Xu, Yibo Yang, Haobo Yuan, Guangliang Cheng, Yunhai Tong, Zhouchen Lin, Ming-Hsuan Yang, DaCheng Tao
Third, inspired by Mask2Former, based on our meta-architecture, we propose Panoptic-PartFormer++ and design a new part-whole cross-attention scheme to boost part segmentation qualities further.
no code implementations • CVPR 2023 • Jiaxian Guo, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Boyang Li, DaCheng Tao, Steven Hoi
To address this issue, we propose Img2Prompt, a plug-and-play module that provides the prompts that can bridge the aforementioned modality and task disconnections, so that LLMs can perform zero-shot VQA tasks without end-to-end training.
no code implementations • CVPR 2023 • Cheng Wen, Baosheng Yu, DaCheng Tao
In this paper, we introduce a new skeleton-aware learning-to-sample method by learning object skeletons as the prior knowledge to preserve the object geometry and topology information during sampling.
no code implementations • CVPR 2023 • Aishan Liu, Shiyu Tang, Siyuan Liang, Ruihao Gong, Boxi Wu, Xianglong Liu, DaCheng Tao
In particular, we comprehensively evaluated 20 most representative adversarially trained architectures on ImageNette and CIFAR-10 datasets towards multiple l_p-norm adversarial attacks.
no code implementations • ICCV 2023 • Heng Zhang, Daqing Liu, Zezhong Lv, Bing Su, DaCheng Tao
Paired video and language data is naturally temporal concurrency, which requires the modeling of the temporal dynamics within each modality and the temporal alignment across modalities simultaneously.
no code implementations • ICCV 2023 • Haotian Wang, Haoang Chi, Wenjing Yang, Zhipeng Lin, Mingyang Geng, Long Lan, Jing Zhang, DaCheng Tao
As a complementary of SDPA, we also propose Target-Combined Deployment Authorization (TPDA), where unauthorized domains are partially accessible, and simplify the DSO method to a perturbation operation on the pseudo predictions, referred to as Target-Dependent Domain-Specified Optimization (TDSO).