no code implementations • ECCV 2020 • Zetong Yang, Yanan sun, Shu Liu, Xiaojuan Qi, Jiaya Jia
In 3D recognition, to fuse multi-scale structure information, existing methods apply hierarchical frameworks stacked by multiple fusion layers for integrating current relative locations with structure information from the previous level.
no code implementations • 9 May 2024 • Yuwei Ou, Yuqi Feng, Yanan sun
To defend deep neural networks from adversarial attacks, adversarial training has been drawing increasing attention for its effectiveness.
1 code implementation • 23 Apr 2024 • Aojun Lu, Tao Feng, Hangjie Yuan, Xiaotian Song, Yanan sun
This paper seeks to bridge this gap between network architecture design and CL, and to present a holistic study on the impact of network architectures on CL.
no code implementations • 20 Mar 2024 • Chengzhe Feng, Yanan sun, Ke Li, Pan Zhou, Jiancheng Lv, Aojun Lu
We conduct GenAP on three popular code intelligence PLMs with three canonical code intelligence tasks including defect prediction, code summarization, and code translation.
no code implementations • 22 Jan 2024 • Zeqiong Lv, Chao Qian, Yanan sun
Evolutionary neural architecture search (ENAS) employs evolutionary algorithms to find high-performing neural architectures automatically, and has achieved great success.
1 code implementation • 29 Dec 2023 • Zetong Yang, Li Chen, Yanan sun, Hongyang Li
To resolve this, we bring up a new pre-training task termed as visual point cloud forecasting - predicting future point clouds from historical visual input.
no code implementations • 1 Dec 2023 • Lin Lu, Chenxi Dai, Wangcheng Tao, Binhang Yuan, Yanan sun, Pan Zhou
Decentralized training of large language models has emerged as an effective way to democratize this technology.
no code implementations • 6 Jul 2023 • Dengfeng Wang, Liukai Xu, Songyuan Liu, Zhi Li, Yiming Chen, Weifeng He, Xueqing Li, Yanan sun
Accommodating all the weights on-chip for large-scale NNs remains a great challenge for SRAM based computing-in-memory (SRAM-CIM) with limited on-chip capacity.
no code implementations • 7 Jun 2023 • Yanan sun, Zihan Zhong, Qi Fan, Chi-Keung Tang, Yu-Wing Tai
Our thorough studies validate that models pre-trained as such can learn rich representations of both modalities, improving their ability to understand how images and text relate to each other.
no code implementations • 18 Apr 2023 • Peng Zeng, Xiaotian Song, Andrew Lensen, Yuwei Ou, Yanan sun, Mengjie Zhang, Jiancheng Lv
With these designs, the proposed DGP method can efficiently search for the GP trees with higher performance, thus being capable of dealing with high-dimensional SR. To demonstrate the effectiveness of DGP, we conducted various experiments against the state of the arts based on both GP and deep neural networks.
no code implementations • ICCV 2023 • Yuhao Zhou, Mingjia Shi, Yuanxi Li, Qing Ye, Yanan sun, Jiancheng Lv
Reducing communication overhead in federated learning (FL) is challenging but crucial for large-scale distributed privacy-preserving machine learning.
no code implementations • 14 Jan 2023 • Xiangning Xie, Xiaotian Song, Zeqiong Lv, Gary G. Yen, Weiping Ding, Yanan sun
In surveying each category, we further discuss the design principles and analyze the strength and weaknesses to clarify the landscape of existing EEMs, thus making easily understanding the research trends of EEMs.
1 code implementation • CVPR 2023 • Yanan sun, Chi-Keung Tang, Yu-Wing Tai
Instead, our method resorts to spatial and temporal sparsity for solving general UHR matting.
no code implementations • 28 Dec 2022 • Yuwei Ou, Xiangning Xie, Shangce Gao, Yanan sun, Kay Chen Tan, Jiancheng Lv
Deep neural networks (DNNs) are found to be vulnerable to adversarial attacks, and various methods have been proposed for the defense.
no code implementations • 23 Dec 2022 • Yuqiao Liu, Haipeng Li, Yanan sun, Shuaicheng Liu
NAS without training (WOT) score is such a metric, which estimates the final trained accuracy of the architecture through the ability to distinguish different inputs in the activation layer.
no code implementations • 21 Nov 2022 • Changlin Li, Guangyang Wu, Yanan sun, Xin Tao, Chi-Keung Tang, Yu-Wing Tai
The learnt deformable kernel is then utilized in convolving the input frames for predicting the interpolated frame.
2 code implementations • NeurIPS 2022 • Yuqiao Liu, Yehui Tang ~Yehui_Tang1, Zeqiong Lv, Yunhe Wang, Yanan sun
To solve this issue, we propose a Cross-Domain Predictor (CDP), which is trained based on the existing NAS benchmark datasets (e. g., NAS-Bench-101), but can be used to find high-performance architectures in large-scale search spaces.
no code implementations • 11 Oct 2022 • Zeqiong Lv, Chao Qian, Gary G. Yen, Yanan sun
Evolutionary computation-based neural architecture search (ENAS) is a popular technique for automating architecture design of deep neural networks.
no code implementations • 17 Sep 2022 • Zhiyao Sun, Yu-Hui Wen, Tian Lv, Yanan sun, Ziyang Zhang, Yaoyuan Wang, Yong-Jin Liu
In this paper, we propose a high-quality facial expression editing method for talking face videos, allowing the user to control the target emotion in the edited video continuously.
no code implementations • 3 Jul 2022 • Xiangning Xie, Yuqiao Liu, Yanan sun, Mengjie Zhang, Kay Chen Tan
Performance predictors can greatly alleviate the prohibitive cost of NAS by directly predicting the performance of DNNs.
1 code implementation • CVPR 2022 • Yanan sun, Chi-Keung Tang, Yu-Wing Tai
A new instance matting metric called instance matting quality (IMQ) is proposed, which addresses the absence of a unified and fair means of evaluation emphasizing both instance recognition and matting quality.
no code implementations • 21 Apr 2022 • Zixuan Liang, Yanan sun
Specifically, the proposed approach is built by learning the knowledge of high-level experts in designing state-of-the-art architectures, and then the new architecture is directly generated upon the knowledge learned.
no code implementations • 13 Apr 2022 • Zipeng Ye, Zhiyao Sun, Yu-Hui Wen, Yanan sun, Tian Lv, Ran Yi, Yong-Jin Liu
In this paper, we propose a method to generate talking-face videos with continuously controllable expressions in real-time.
1 code implementation • CVPR 2022 • Zetong Yang, Li Jiang, Yanan sun, Bernt Schiele, Jiaya Jia
This is achieved by introducing an intermediate representation, i. e., Q-representation, in the querying stage to serve as a bridge between the embedding stage and task heads.
Ranked #7 on Semantic Segmentation on S3DIS
no code implementations • 15 Nov 2021 • Yuhan Fang, Yuqiao Liu, Yanan sun
As a consequence, it requires the designers to develop expertise in both CF and DNNs, which limits the application of deep learning methods in CF and the accuracy of recommended results.
1 code implementation • 9 Aug 2021 • Xiangning Xie, Yuqiao Liu, Yanan sun, Gary G. Yen, Bing Xue, Mengjie Zhang
The paper conducts efficient comparison experiments on eight ENAS algorithms with high GPU utilization on this platform.
1 code implementation • ICCV 2021 • Yuqiao Liu, Yehui Tang, Yanan sun
Specifically, a homogeneous architecture augmentation algorithm is proposed in HAAP to generate sufficient training data taking the use of homogeneous representation.
no code implementations • CVPR 2021 • Yu-Hui Wen, Zhipeng Yang, Hongbo Fu, Lin Gao, Yanan sun, Yong-Jin Liu
Motion style transfer is an important problem in many computer graphics and computer vision applications, including human animation, games, and robotics.
no code implementations • 3 May 2021 • Jindi Lv, Qing Ye, Yanan sun, Juan Zhao, Jiancheng Lv
In this paper, we propose a novel approach, Heart-Darts, to efficiently classify the ECG signals by automatically designing the CNN model with the differentiable architecture search (i. e., Darts, a cell-based neural architecture search method).
1 code implementation • CVPR 2021 • Yanan sun, Guanzhi Wang, Qiao Gu, Chi-Keung Tang, Yu-Wing Tai
Despite the significant progress made by deep learning in natural image matting, there has been so far no representative work on deep learning for video matting due to the inherent technical challenges in reasoning temporal domain and lack of large-scale video matting datasets.
1 code implementation • CVPR 2021 • Yanan sun, Chi-Keung Tang, Yu-Wing Tai
Specifically, we consider and learn 20 classes of matting patterns, and propose to extend the conventional trimap to semantic trimap.
no code implementations • 6 Sep 2020 • Qing Ye, Yuxuan Han, Yanan sun, Jiancheng Lv
Synchronous methods are widely used in distributed training the Deep Neural Networks (DNNs).
no code implementations • 30 Aug 2020 • Yanan Sun, Xian Sun, Yuhan Fang, Gary Yen
Performance predictors are a type of regression models which can assist to accomplish the search, while without exerting much computational resource.
no code implementations • 25 Aug 2020 • Yuqiao Liu, Yanan sun, Bing Xue, Mengjie Zhang, Gary G. Yen, Kay Chen Tan
Deep Neural Networks (DNNs) have achieved great success in many applications.
no code implementations • 15 Aug 2020 • Yuqiao Liu, Yanan sun, Bing Xue, Mengjie Zhang
Hyperspectral images (HSIs) are susceptible to various noise factors leading to the loss of information, and the noise restricts the subsequent HSIs object detection and classification tasks.
1 code implementation • ECCV 2020 • Lei Ke, Shichao Li, Yanan sun, Yu-Wing Tai, Chi-Keung Tang
GSNet utilizes a unique four-way feature extraction and fusion scheme and directly regresses 6DoF poses and shapes in a single forward pass.
Ranked #1 on Autonomous Driving on ApolloCar3D
1 code implementation • 23 Jul 2020 • Qing Ye, Yuhao Zhou, Mingjia Shi, Yanan sun, Jiancheng Lv
Specifically, the performance of each worker is evaluatedfirst based on the fact in the previous epoch, and then the batch size and datasetpartition are dynamically adjusted in consideration of the current performanceof the worker, thereby improving the utilization of the cluster.
1 code implementation • 15 Mar 2020 • Zipeng Ye, Mengfei Xia, Yanan sun, Ran Yi, MinJing Yu, Juyong Zhang, Yu-Kun Lai, Yong-Jin Liu
The most challenging issue for our system is that the source domain of face photos (characterized by normal 2D faces) is significantly different from the target domain of 3D caricatures (characterized by 3D exaggerated face shapes and textures).
2 code implementations • CVPR 2020 • Zetong Yang, Yanan sun, Shu Liu, Jiaya Jia
Our method outperforms all state-of-the-art voxel-based single stage methods by a large margin, and has comparable performance to two stage point-based methods as well, with inference speed more than 25 FPS, 2x faster than former state-of-the-art point-based methods.
no code implementations • 16 Feb 2020 • Yanan Sun, Ziyao Ren, Gary G. Yen, Bing Xue, Mengjie Zhang, Jiancheng Lv
Data mining on existing CNN can discover useful patterns and fundamental sub-comments from their architectures, providing researchers with strong prior knowledge to design proper CNN architectures when they have no expertise in CNNs.
no code implementations • ICCV 2019 • Zetong Yang, Yanan sun, Shu Liu, Xiaoyong Shen, Jiaya Jia
We present a new two-stage 3D object detection framework, named sparse-to-dense 3D Object Detector (STD).
1 code implementation • 21 Mar 2019 • Bin Wang, Yanan sun, Bing Xue, Mengjie Zhang
In recent years, convolutional neural networks (CNNs) have become deeper in order to achieve better classification accuracy in image classification.
no code implementations • 10 Mar 2019 • Bin Wang, Yanan sun, Bing Xue, Mengjie Zhang
Three major contributions of this work are: Firstly, a new encoding strategy is proposed to encode a CNN, where the architecture and the shortcut connections are encoded separately; Secondly, a hybrid two-level EC method, which combines particle swarm optimisation and genetic algorithms, is developed to search for the optimal CNNs; Lastly, an adjustable learning rate is introduced for the fitness evaluations, which provides a better learning rate for the training process given a fixed number of epochs.
no code implementations • 13 Dec 2018 • Zetong Yang, Yanan sun, Shu Liu, Xiaoyong Shen, Jiaya Jia
We present a novel 3D object detection framework, named IPOD, based on raw point cloud.
Ranked #1 on 3D Object Detection on KITTI Pedestrians Easy
no code implementations • 28 Oct 2018 • Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen
The proposed algorithm is evaluated on CIFAR10 and CIFAR100 against 18 state-of-the-art peer competitors.
no code implementations • 20 Aug 2018 • Bin Wang, Yanan sun, Bing Xue, Mengjie Zhang
In this paper, a new hybrid differential evolution (DE) algorithm with a newly added crossover operator is proposed to evolve the architectures of CNNs of any lengths, which is named DECNN.
4 code implementations • 11 Aug 2018 • Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen
Convolutional Neural Networks (CNNs) have gained a remarkable success on many image classification tasks in recent years.
no code implementations • 17 Mar 2018 • Bin Wang, Yanan sun, Bing Xue, Mengjie Zhang
Convolutional neural networks (CNNs) are one of the most effective deep learning methods to solve image classification problems, but the best architecture of a CNN to solve a specific problem can be extremely complicated and hard to design.
no code implementations • 24 Feb 2018 • Yanan Sun, Gary G. Yen, Zhang Yi
Finally, by assigning the Pareto-optimal solutions to the uniformly distributed reference vectors, a set of solutions with excellent diversity and convergence is obtained.
no code implementations • 24 Feb 2018 • Yanan Sun, Gary G. Yen, Zhang Yi
Inverted Generational Distance (IGD) has been widely considered as a reliable performance indicator to concurrently quantify the convergence and diversity of multi- and many-objective evolutionary algorithms.
no code implementations • 13 Dec 2017 • Yanan Sun, Gary G. Yen, Zhang Yi
Specifically, error classification rate on MNIST with $1. 15\%$ is reached by the proposed algorithm consistently, which is a very promising result against state-of-the-art unsupervised DL algorithms.
1 code implementation • 13 Dec 2017 • Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen
Convolutional auto-encoders have shown their remarkable performance in stacking to deep convolutional neural networks for classifying image data during past several years.
1 code implementation • 30 Oct 2017 • Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen
Evolutionary computation methods have been successfully applied to neural networks since two decades ago, while those methods cannot scale well to the modern deep neural networks due to the complicated architectures and large quantities of connection weights.