no code implementations • ECCV 2020 • Fang Zhao, Shengcai Liao, Guo-Sen Xie, Jian Zhao, Kaihao Zhang, Ling Shao
On the other hand, mutual instance selection further selects reliable and informative instances for training according to the peer-confidence and relationship disagreement of the networks.
no code implementations • ECCV 2020 • Jin Xie, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan, Yanwei Pang, Ling Shao, Mubarak Shah
We further introduce a count-and-similarity branch within the two-stage detection framework, which predicts pedestrian count as well as proposal similarity.
no code implementations • ECCV 2020 • Jiaxin Chen, Jie Qin, Yuming Shen, Li Liu, Fan Zhu, Ling Shao
This paper proposes a novel method for 3D shape representation learning, namely Hyperbolic Embedded Attentive Representation (HEAR).
1 code implementation • ECCV 2020 • Xingping Dong, Jianbing Shen, Ling Shao, Fatih Porikli
To make full use of these sequence-specific samples, {we propose a compact latent network to quickly adjust the tracking model to adapt to new scenes.}
1 code implementation • ECCV 2020 • Deng-Ping Fan, Yingjie Zhai, Ali Borji, Jufeng Yang, Ling Shao
In particular, we 1) propose a bifurcated backbone strategy (BBS) to split the multi-level features into teacher and student features, and 2) utilize a depth-enhanced module (DEM) to excavate informative parts of depth cues from the channel and spatial views.
no code implementations • ECCV 2020 • Guo-Sen Xie, Li Liu, Fan Zhu, Fang Zhao, Zheng Zhang, Yazhou Yao, Jie Qin, Ling Shao
To exploit the progressive interactions among these regions, we represent them as a region graph, on which the parts relation reasoning is performed with graph convolutions, thus leading to our PRR branch.
no code implementations • 13 May 2024 • Xueying Jiang, Sheng Jin, Xiaoqin Zhang, Ling Shao, Shijian Lu
With the proposed object occlusion and completion, MonoMAE learns enriched 3D representations that achieve superior monocular 3D detection performance qualitatively and quantitatively for both occluded and non-occluded objects.
no code implementations • 12 Mar 2024 • Kunhao Liu, Fangneng Zhan, Muyu Xu, Christian Theobalt, Ling Shao, Shijian Lu
We introduce StyleGaussian, a novel 3D style transfer technique that allows instant transfer of any image's style to a 3D scene at 10 frames per second (fps).
1 code implementation • 11 Mar 2024 • Guobao Xiao, Jun Yu, Jiayi Ma, Deng-Ping Fan, Ling Shao
The principle of LSC is to preserve the latent semantic consensus in both data points and model hypotheses.
no code implementations • 6 Feb 2024 • Aoran Xiao, Weihao Xuan, Heli Qi, Yun Xing, Ruijie Ren, Xiaoqin Zhang, Ling Shao, Shijian Lu
CAT-SAM freezes the entire SAM and adapts its mask decoder and image encoder simultaneously with a small number of learnable parameters.
1 code implementation • 5 Feb 2024 • Sheng Luo, Wei Chen, Wanxin Tian, Rui Liu, Luanxuan Hou, Xiubao Zhang, Haifeng Shen, Ruiqi Wu, Shuyi Geng, Yi Zhou, Ling Shao, Yi Yang, Bojun Gao, Qun Li, Guobin Wu
Foundation models have indeed made a profound impact on various fields, emerging as pivotal components that significantly shape the capabilities of intelligent systems.
no code implementations • 15 Jan 2024 • Hao Tang, Ling Shao, Nicu Sebe, Luc van Gool
Finally, we propose a novel self-guided pre-training method for graph representation learning.
Generative Adversarial Network Graph Representation Learning +1
no code implementations • 13 Jan 2024 • Kai Jiang, Jiaxing Huang, Weiying Xie, Yunsong Li, Ling Shao, Shijian Lu
Camera-only Bird's Eye View (BEV) has demonstrated great potential in environment perception in a 3D space.
no code implementations • 13 Jan 2024 • Kai Jiang, Jiaxing Huang, Weiying Xie, Jie Lei, Yunsong Li, Ling Shao, Shijian Lu
Large-vocabulary object detectors (LVDs) aim to detect objects of many categories, which learn super objectness features and can locate objects accurately while applied to various downstream data.
2 code implementations • NeurIPS 2023 • Yun Xing, Jian Kang, Aoran Xiao, Jiahao Nie, Ling Shao, Shijian Lu
Such semantic misalignment circulates in pre-training, leading to inferior zero-shot performance in dense predictions due to insufficient visual concepts captured in textual representations.
no code implementations • 15 Sep 2023 • Zhimeng Xin, Tianxu Wu, Shiming Chen, Yixiong Zou, Ling Shao, Xinge You
Extensive experiments on the PASCAL VOC and COCO datasets show that our ECEA module can assist the few-shot detector to completely predict the object despite some regions failing to appear in the training samples and achieve the new state of the art compared with existing FSOD methods.
no code implementations • ICCV 2023 • Jiahui Zhang, Fangneng Zhan, Yingchen Yu, Kunhao Liu, Rongliang Wu, Xiaoqin Zhang, Ling Shao, Shijian Lu
However, as the pose estimator is trained with only rendered images, the pose estimation is usually biased or inaccurate for real images due to the domain gap between real images and rendered images, leading to poor robustness for the pose estimation of real images and further local minima in joint optimization.
no code implementations • 21 Aug 2023 • Xinghong Liu, Yi Zhou, Tao Zhou, Chun-Mei Feng, Ling Shao
SF-UniDA methods eliminate the need for direct access to source samples when performing adaptation to the target domain.
no code implementations • ICCV 2023 • Muyu Xu, Fangneng Zhan, Jiahui Zhang, Yingchen Yu, Xiaoqin Zhang, Christian Theobalt, Ling Shao, Shijian Lu
Neural Radiance Field (NeRF) has shown impressive performance in novel view synthesis via implicit scene representation.
1 code implementation • 31 May 2023 • Aoran Xiao, Xiaoqin Zhang, Ling Shao, Shijian Lu
We address three critical questions in this emerging research field: i) the importance and urgency of label-efficient learning in point cloud processing, ii) the subfields it encompasses, and iii) the progress achieved in this area.
no code implementations • IEEE Transactions on Cybernetics 2023 • Lisha Cui, Pei Lv, Xiaoheng Jiang, Zhimin Gao, Bing Zhou, Luming Zhang, Ling Shao, Mingliang Xu
State-of-the-art object detectors usually progressively downsample the input image until it is represented by small feature maps, which loses the spatial information and compromises the representation of small objects.
Ranked #1 on Traffic Sign Detection on TT100K
no code implementations • CVPR 2023 • Hao Tang, Zhenyu Zhang, Humphrey Shi, Bo Li, Ling Shao, Nicu Sebe, Radu Timofte, Luc van Gool
We present a novel graph Transformer generative adversarial network (GTGAN) to learn effective graph node relations in an end-to-end fashion for the challenging graph-constrained house generation task.
no code implementations • 2 Feb 2023 • Xingping Dong, Jianbing Shen, Fatih Porikli, Jiebo Luo, Ling Shao
Under this viewing, we perform an in-depth analysis for them through visual simulations and real tracking examples, and find that the failure cases in some challenging situations can be regarded as the issue of missing decisive samples in offline training.
no code implementations • 19 Nov 2022 • Chenyi Jiang, Dubing Chen, Shidong Wang, Yuming Shen, Haofeng Zhang, Ling Shao
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen compositions from seen states and objects.
1 code implementation • 12 Nov 2022 • Hao Tang, Ling Shao, Philip H. S. Torr, Nicu Sebe
To further capture the change in pose of each part more precisely, we propose a novel part-aware bipartite graph reasoning (PBGR) block to decompose the task of reasoning the global structure transformation with a bipartite graph into learning different local transformations for different semantic body/face parts.
1 code implementation • 27 Sep 2022 • Xingping Dong, Jianbing Shen, Ling Shao
In this work, we prove that the core reason for this is lack of a clustering-friendly property in the embedding space.
no code implementations • TIP 2022 • Tiantian Geng, Feng Zheng, Xiaorong Hou, Ke Lu, Guo-Jun Qi, Ling Shao
Spatial-temporal relation reasoning is a significant yet challenging problem for video action recognition.
Ranked #35 on Action Recognition on Something-Something V1
2 code implementations • 30 Jul 2022 • Aoran Xiao, Jiaxing Huang, Dayan Guan, Kaiwen Cui, Shijian Lu, Ling Shao
The first is scene-level swapping which exchanges point cloud sectors of two LiDAR scans that are cut along the azimuth axis.
no code implementations • 14 Jul 2022 • Xingping Dong, Shengcai Liao, Bo Du, Ling Shao
Most existing few-shot learning (FSL) methods require a large amount of labeled data in meta-training, which is a major limit.
no code implementations • 8 Jul 2022 • Jinpeng Li, Haibo Jin, Shengcai Liao, Ling Shao, Pheng-Ann Heng
This paper presents a Refinement Pyramid Transformer (RePFormer) for robust facial landmark detection.
1 code implementation • CVPR 2022 • Yuanwei Liu, Nian Liu, Qinglong Cao, Xiwen Yao, Junwei Han, Ling Shao
Then, a BG Eliminating Module and a DO Eliminating Module are proposed to successively filter out the BG and DO information from the query feature, based on which we can obtain a BG and DO-free target object segmentation result.
no code implementations • 25 Apr 2022 • Minghui Chen, Cheng Wen, Feng Zheng, Fengxiang He, Ling Shao
The tangent transfer creates initial augmented samples for improving corruption robustness.
2 code implementations • 19 Apr 2022 • Bing Wang, Zhengdi Yu, Bo Yang, Jie Qin, Toby Breckon, Ling Shao, Niki Trigoni, Andrew Markham
We present RangeUDF, a new implicit representation based framework to recover the geometry and semantics of continuous 3D scene surfaces from point clouds.
1 code implementation • 19 Apr 2022 • Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, Ling Shao
In the former case, spatial details are preserved but the contextual information cannot be precisely encoded.
1 code implementation • CVPR 2022 • Yunhua Zhang, Hazel Doughty, Ling Shao, Cees G. M. Snoek
This paper strives for activity recognition under domain shift, for example caused by change of scenery or camera viewpoint.
1 code implementation • 26 Mar 2022 • Jinyu Yang, Zhe Li, Song Yan, Feng Zheng, Aleš Leonardis, Joni-Kristian Kämäräinen, Ling Shao
Particularly, we are the first to provide depth quality evaluation and analysis of tracking results in depth-friendly scenarios in RGBD tracking.
1 code implementation • 22 Mar 2022 • Xiaobin Hu, Shuo Wang, Xuebin Qin, Hang Dai, Wenqi Ren, Ying Tai, Chengjie Wang, Ling Shao
Spotting camouflaged objects that are visually assimilated into the background is tricky for both object detection algorithms and humans who are usually confused or cheated by the perfectly intrinsic similarities between the foreground objects and the background surroundings.
1 code implementation • 6 Mar 2022 • Xuebin Qin, Hang Dai, Xiaobin Hu, Deng-Ping Fan, Ling Shao, and Luc Van Gool
We present a systematic study on a new task called dichotomous image segmentation (DIS) , which aims to segment highly accurate objects from natural images.
Ranked #5 on Dichotomous Image Segmentation on DIS-TE1
1 code implementation • 28 Feb 2022 • Aoran Xiao, Jiaxing Huang, Dayan Guan, Xiaoqin Zhang, Shijian Lu, Ling Shao
The convergence of point cloud and DNNs has led to many deep point cloud models, largely trained under the supervision of large-scale and densely-labelled point cloud data.
1 code implementation • 28 Feb 2022 • Hao Tang, Ling Shao, Philip H. S. Torr, Nicu Sebe
To learn more discriminative class-specific feature representations for the local generation, we also propose a novel classification module.
1 code implementation • ICLR 2022 • Zehao Xiao, XianTong Zhen, Ling Shao, Cees G. M. Snoek
We leverage a meta-learning paradigm to learn our model to acquire the ability of adaptation with single samples at training time so as to further adapt itself to each single test sample at test time.
Ranked #1 on Domain Adaptation on PACS
1 code implementation • 15 Feb 2022 • Mingbao Lin, Liujuan Cao, Yuxin Zhang, Ling Shao, Chia-Wen Lin, Rongrong Ji
Then, we introduce a recommendation-based filter selection scheme where each filter recommends a group of its closest filters.
no code implementations • 10 Feb 2022 • Tao Zhou, Huazhu Fu, Chen Gong, Ling Shao, Fatih Porikli, Haibin Ling, Jianbing Shen
Besides, a novel constraint based on the Hilbert Schmidt Independence Criterion (HSIC) is introduced to ensure the diversity of multi-level subspace representations, which enables the complementarity of multi-level representations to be explored to boost the transfer learning performance.
2 code implementations • 10 Jan 2022 • Irtiza Hasan, Shengcai Liao, Jinpeng Li, Saad Ullah Akram, Ling Shao
As for the data, we show that the autonomous driving benchmarks are monotonous in nature, that is, they are not diverse in scenarios and dense in pedestrians.
no code implementations • CVPR 2022 • Dongming Wu, Xingping Dong, Ling Shao, Jianbing Shen
To address this, we propose a novel multi-level representation learning approach, which explores the inherent structure of the video content to provide a set of discriminative visual embedding, enabling more effective vision-language semantic alignment.
no code implementations • 28 Dec 2021 • Peng Tu, Yawen Huang, Feng Zheng, Zhenyu He, Liujun Cao, Ling Shao
In this paper, we propose a novel method for semi-supervised semantic segmentation named GuidedMix-Net, by leveraging labeled information to guide the learning of unlabeled instances.
no code implementations • 26 Dec 2021 • Mohammad Mahdi Derakhshani, XianTong Zhen, Ling Shao, Cees G. M. Snoek
Kernel continual learning by \citet{derakhshani2021kernel} has recently emerged as a strong continual learner due to its non-parametric ability to tackle task interference and catastrophic forgetting.
1 code implementation • 16 Dec 2021 • Shiming Chen, Ziming Hong, Wenjin Hou, Guo-Sen Xie, Yibing Song, Jian Zhao, Xinge You, Shuicheng Yan, Ling Shao
Analogously, VAT uses the similar feature augmentation encoder to refine the visual features, which are further applied in visual$\rightarrow$attribute decoder to learn visual-based attribute features.
1 code implementation • ICLR 2022 • Yingjun Du, XianTong Zhen, Ling Shao, Cees G. M. Snoek
To explore and exploit the importance of different semantic levels, we further propose to learn the weights associated with the prototype at each level in a data-driven way, which enables the model to adaptively choose the most generalizable features.
1 code implementation • 9 Dec 2021 • Chun-Mei Feng, Yunlu Yan, Shanshan Wang, Yong Xu, Ling Shao, Huazhu Fu
The core idea is to divide the MR reconstruction model into two parts: a globally shared encoder to obtain a generalized representation at the global level, and a client-specific decoder to preserve the domain-specific properties of each client, which is important for collaborative reconstruction when the clients have unique distribution.
1 code implementation • journal 2021 • Tianfei Zhou, Liulei Li, Xueyi Li, Chun-Mei Feng, Jianwu Li, Ling Shao
The framework explicitly encodes semantic dependencies in a group of images to discover rich semantic context for estimating more reliable pseudo ground-truths, which are subsequently employed to train more effective segmentation models.
no code implementations • 10 Nov 2021 • Jiayi Shen, XianTong Zhen, Marcel Worring, Ling Shao
Our multi-task neural processes methodologically expand the scope of vanilla neural processes and provide a new way of exploring task relatedness in function spaces for multi-task learning.
1 code implementation • NeurIPS 2021 • Jiayi Shen, XianTong Zhen, Marcel Worring, Ling Shao
Multi-task learning aims to explore task relatedness to improve individual tasks, which is of particular significance in the challenging scenario that only limited data is available for each task.
2 code implementations • 15 Oct 2021 • Chun-Mei Feng, Huazhu Fu, Tianfei Zhou, Yong Xu, Ling Shao, David Zhang
Magnetic resonance (MR) imaging produces detailed images of organs and tissues with better contrast, but it suffers from a long acquisition time, which makes the image quality vulnerable to say motion artifacts.
1 code implementation • 2 Oct 2021 • Nian Liu, Wangbo Zhao, Dingwen Zhang, Junwei Han, Ling Shao
On the other hand, instead of processing the twokinds of data separately, we build a novel dual graph modelto guide the focal stack fusion process using all-focus pat-terns.
1 code implementation • ICCV 2021 • Ni Zhang, Junwei Han, Nian Liu, Ling Shao
In this paper, we propose a novel consensus-aware dynamic convolution model to explicitly and effectively perform the "summarize and search" process.
Ranked #3 on Co-Salient Object Detection on CoSal2015
2 code implementations • NeurIPS 2021 • Shiming Chen, Guo-Sen Xie, Yang Liu, Qinmu Peng, Baigui Sun, Hao Li, Xinge You, Ling Shao
Specifically, HSVA aligns the semantic and visual domains by adopting a hierarchical two-step adaptation, i. e., structure adaptation and distribution adaptation.
1 code implementation • ICCV 2021 • Jing Zhang, Deng-Ping Fan, Yuchao Dai, Xin Yu, Yiran Zhong, Nick Barnes, Ling Shao
In this paper, we introduce a novel multi-stage cascaded learning framework via mutual information minimization to "explicitly" model the multi-modal information between RGB image and depth data.
1 code implementation • 3 Sep 2021 • Chun-Mei Feng, Yunlu Yan, Kai Yu, Yong Xu, Ling Shao, Huazhu Fu
Our SANet could explore the areas of high-intensity and low-intensity regions in the "forward" and "reverse" directions with the help of the auxiliary contrast, while learning clearer anatomical structure and edge information for the SR of a target-contrast MR image.
no code implementations • ICCV 2021 • Hongjun Chen, Jinbao Wang, Hong Cai Chen, XianTong Zhen, Feng Zheng, Rongrong Ji, Ling Shao
Annotation burden has become one of the biggest barriers to semantic segmentation.
Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation
1 code implementation • ICCV 2021 • Sanath Narayan, Akshita Gupta, Salman Khan, Fahad Shahbaz Khan, Ling Shao, Mubarak Shah
We note that the best existing multi-label ZSL method takes a shared approach towards attending to region features with a common set of attention maps for all the classes.
Ranked #2 on Multi-label zero-shot learning on Open Images V4
1 code implementation • ICCV 2021 • Fang Zhao, Wenhao Wang, Shengcai Liao, Ling Shao
While single-view 3D reconstruction has made significant progress benefiting from deep shape representations in recent years, garment reconstruction is still not solved well due to open surfaces, diverse topologies and complex geometric details.
2 code implementations • 16 Aug 2021 • Bo Dong, Wenhai Wang, Deng-Ping Fan, Jinpeng Li, Huazhu Fu, Ling Shao
Unlike existing CNN-based methods, we adopt a transformer encoder, which learns more powerful and robust representations.
Ranked #9 on Medical Image Segmentation on CVC-ColonDB
1 code implementation • 8 Aug 2021 • Jiale Li, Hang Dai, Ling Shao, Yong Ding
In this paper, we present an Intersection-over-Union (IoU) guided two-stage 3D object detector with a voxel-to-point decoder.
2 code implementations • 8 Aug 2021 • Jiale Li, Hang Dai, Ling Shao, Yong Ding
We propose an attentive module to fit the sparse feature maps to dense mostly on the object regions through the deformable convolution tower and the supervised mask-guided attention.
1 code implementation • ICCV 2021 • Ge-Peng Ji, Deng-Ping Fan, Keren Fu, Zhe Wu, Jianbing Shen, Ling Shao
Previous video object segmentation approaches mainly focus on using simplex solutions between appearance and motion, limiting feature collaboration efficiency among and across these two cues.
Ranked #7 on Video Polyp Segmentation on SUN-SEG-Hard (Unseen)
1 code implementation • ICCV 2021 • Shiming Chen, Wenjie Wang, Beihao Xia, Qinmu Peng, Xinge You, Feng Zheng, Ling Shao
FREE employs a feature refinement (FR) module that incorporates \textit{semantic$\rightarrow$visual} mapping into a unified generative model to refine the visual features of seen and unseen class samples.
no code implementations • 15 Jul 2021 • Ivona Najdenkoska, XianTong Zhen, Marcel Worring, Ling Shao
The topics are inferred in a conditional variational inference framework, with each topic governing the generation of a sentence in the report.
no code implementations • 12 Jul 2021 • Shivam Chandhok, Sanath Narayan, Hisham Cholakkal, Rao Muhammad Anwer, Vineeth N Balasubramanian, Fahad Shahbaz Khan, Ling Shao
The need to address the scarcity of task-specific annotated data has resulted in concerted efforts in recent years for specific settings such as zero-shot learning (ZSL) and domain generalization (DG), to separately address the issues of semantic shift and domain shift, respectively.
1 code implementation • 12 Jul 2021 • Mohammad Mahdi Derakhshani, XianTong Zhen, Ling Shao, Cees G. M. Snoek
We further introduce variational random features to learn a data-driven kernel for each task.
no code implementations • 10 Jul 2021 • Jinpeng Li, Yichao Yan, Shengcai Liao, Xiaokang Yang, Ling Shao
Transformers have demonstrated great potential in computer vision tasks.
no code implementations • 8 Jul 2021 • Nian Liu, Long Li, Wangbo Zhao, Junwei Han, Ling Shao
Conventional salient object detection models cannot differentiate the importance of different salient objects.
1 code implementation • 29 Jun 2021 • Peng Tu, Yawen Huang, Rongrong Ji, Feng Zheng, Ling Shao
To take advantage of the labeled examples and guide unlabeled data learning, we further propose a mask generation module to generate high-quality pseudo masks for the unlabeled data.
1 code implementation • 27 Jun 2021 • Chun-Mei Feng, Yunlu Yan, Geng Chen, Yong Xu, Ling Shao, Huazhu Fu
To this end, we propose a multi-modal transformer (MTrans), which is capable of transferring multi-scale features from the target modality to the auxiliary modality, for accelerated MR imaging.
16 code implementations • 25 Jun 2021 • Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, Ling Shao
We hope this work will facilitate state-of-the-art Transformer researches in computer vision.
Ranked #23 on Object Detection on COCO-O
no code implementations • ICCV 2021 • Fangneng Zhan, Changgong Zhang, WenBo Hu, Shijian Lu, Feiying Ma, Xuansong Xie, Ling Shao
Accurate lighting estimation is challenging yet critical to many computer vision and computer graphics tasks such as high-dynamic-range (HDR) relighting.
no code implementations • CVPR 2021 • Yawen Huang, Feng Zheng, Danyang Wang, Weilin Huang, Matthew R. Scott, Ling Shao
Recent advances in neuroscience have highlighted the effectiveness of multi-modal medical data for investigating certain pathologies and understanding human cognition.
1 code implementation • CVPR 2021 • Guo-Sen Xie, Jie Liu, Huan Xiong, Ling Shao
However, they fail to fully leverage the high-order appearance relationships between multi-scale features among the support-query image pairs, thus leading to an inaccurate localization of the query objects.
3 code implementations • 19 Jun 2021 • Yichao Yan, Jinpeng Li, Shengcai Liao, Jie Qin, Bingbing Ni, Xiaokang Yang, Ling Shao
This paper inventively considers weakly supervised person search with only bounding box annotations.
no code implementations • 10 Jun 2021 • Hongsong Wang, Shengcai Liao, Ling Shao
Last but not least, we introduce a region feature alignment and an instance discriminator to learn domain-invariant features for object proposals.
1 code implementation • CVPR 2022 • Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu, Ling Shao
In this work, we explore the idea of instance contrastive learning in unsupervised domain adaptation (UDA) and propose a novel Category Contrast technique (CaCo) that introduces semantic priors on top of instance discrimination for visual UDA tasks.
no code implementations • NeurIPS 2021 • Yuming Shen, Ziyi Shen, Menghan Wang, Jie Qin, Philip H. S. Torr, Ling Shao
On one hand, with the corresponding assignment variables being the weight, a weighted aggregation along the data points implements the set representation of a cluster.
2 code implementations • NeurIPS 2021 • Shengcai Liao, Ling Shao
In this work, we further investigate the possibility of applying Transformers for image matching and metric learning given pairs of images.
Ranked #1 on Generalizable Person Re-identification on Market-1501 (using extra training data)
1 code implementation • 28 May 2021 • Guanglei Yang, Hao Tang, Zhun Zhong, Mingli Ding, Ling Shao, Nicu Sebe, Elisa Ricci
In this paper, we study the task of source-free domain adaptation (SFDA), where the source data are not available during target adaptation.
no code implementations • 27 May 2021 • Haibo Jin, Jinpeng Li, Shengcai Liao, Ling Shao
To this end, we first propose a baseline model equipped with one transformer decoder as detection head.
Ranked #5 on Face Alignment on COFW
no code implementations • NeurIPS 2021 • Gengchen Duan, Taisong Jin, Rongrong Ji, Ling Shao, Baochang Zhang, Feiyue Huang, Yongjian Wu
In this article, we propose a novel auxiliary learning induced graph convolutional network in a multi-task fashion.
3 code implementations • 18 May 2021 • Ge-Peng Ji, Yu-Cheng Chou, Deng-Ping Fan, Geng Chen, Huazhu Fu, Debesh Jha, Ling Shao
Existing video polyp segmentation (VPS) models typically employ convolutional neural networks (CNNs) to extract features.
Ranked #6 on Video Polyp Segmentation on SUN-SEG-Easy (Unseen)
1 code implementation • 14 May 2021 • Haoliang Sun, Xiankai Lu, Haochen Wang, Yilong Yin, XianTong Zhen, Cees G. M. Snoek, Ling Shao
We define a global latent variable to represent the prototype of each object category, which we model as a probabilistic distribution.
no code implementations • 12 May 2021 • Chun-Mei Feng, Zhanyuan Yang, Huazhu Fu, Yong Xu, Jian Yang, Ling Shao
In this paper, we propose the Dual-Octave Network (DONet), which is capable of learning multi-scale spatial-frequency features from both the real and imaginary components of MR data, for fast parallel MR image reconstruction.
1 code implementation • 9 May 2021 • Zehao Xiao, Jiayi Shen, XianTong Zhen, Ling Shao, Cees G. M. Snoek
Domain generalization is challenging due to the domain shift and the uncertainty caused by the inaccessibility of target domain data.
no code implementations • 8 May 2021 • Yingjun Du, Haoliang Sun, XianTong Zhen, Jun Xu, Yilong Yin, Ling Shao, Cees G. M. Snoek
Specifically, we propose learning variational random features in a data-driven manner to obtain task-specific kernels by leveraging the shared knowledge provided by related tasks in a meta-learning setting.
2 code implementations • 7 May 2021 • Deng-Ping Fan, Jing Zhang, Gang Xu, Ming-Ming Cheng, Ling Shao
This design bias has led to a saturation in performance for state-of-the-art SOD models when evaluated on existing datasets.
1 code implementation • 3 May 2021 • Jie Hu, Liujuan Cao, Yao Lu, Shengchuan Zhang, Yan Wang, Ke Li, Feiyue Huang, Ling Shao, Rongrong Ji
However, such an upgrade is not applicable to instance segmentation, due to its significantly higher output dimensions compared to object detection.
Ranked #21 on Instance Segmentation on COCO test-dev
1 code implementation • CVPR 2020 • Yichao Yan, Jie Qin1, Jiaxin Chen, Li Liu, Fan Zhu, Ying Tai, Ling Shao
In each hypergraph, different temporal granularities are captured by hyperedges that connect a set of graph nodes (i. e., part-based features) across different temporal ranges.
Ranked #6 on Person Re-Identification on iLIDS-VID
1 code implementation • 29 Apr 2021 • Yichao Yan, Jie Qin, Bingbing Ni, Jiaxin Chen, Li Liu, Fan Zhu, Wei-Shi Zheng, Xiaokang Yang, Ling Shao
Extensive experiments on the novel dataset as well as three existing datasets clearly demonstrate the effectiveness of the proposed framework for both group-based re-id tasks.
1 code implementation • ICCV 2021 • Nian Liu, Ni Zhang, Kaiyuan Wan, Ling Shao, Junwei Han
We also develop a token-based multi-task decoder to simultaneously perform saliency and boundary detection by introducing task-related tokens and a novel patch-task-attention mechanism.
Ranked #1 on RGB-D Salient Object Detection on NJUD
1 code implementation • 12 Apr 2021 • Chun-Mei Feng, Zhanyuan Yang, Geng Chen, Yong Xu, Ling Shao
We evaluate the performance of the proposed model on the acceleration of multi-coil MR image reconstruction.
no code implementations • CVPR 2021 • Tianfei Zhou, Jianwu Li, Xueyi Li, Ling Shao
To address this, we introduce a novel approach for more accurate and efficient spatio-temporal segmentation.
1 code implementation • CVPR 2022 • Shengcai Liao, Ling Shao
Though online hard example mining has improved the learning efficiency to some extent, the mining in mini batches after random sampling is still limited.
Ranked #2 on Generalizable Person Re-identification on Market-1501 (using extra training data)
1 code implementation • CVPR 2021 • Mingchen Zhuge, Dehong Gao, Deng-Ping Fan, Linbo Jin, Ben Chen, Haoming Zhou, Minghui Qiu, Ling Shao
We present a new vision-language (VL) pre-training model dubbed Kaleido-BERT, which introduces a novel kaleido strategy for fashion cross-modality representations from transformers.
1 code implementation • 26 Mar 2021 • Shaojie Li, Mingbao Lin, Yan Wang, Yongjian Wu, Yonghong Tian, Ling Shao, Rongrong Ji
Besides, a self-distillation module is adopted to convert the feature map of deeper layers into a shallower one.
1 code implementation • CVPR 2021 • Shujie Luo, Hang Dai, Ling Shao, Yong Ding
In the first step, the shape alignment is performed to enable the receptive field of the feature map to focus on the pre-defined anchors with high confidence scores.
1 code implementation • CVPR 2021 • Yunhua Zhang, Ling Shao, Cees G. M. Snoek
We also introduce a variant of this dataset for repetition counting under challenging vision conditions.
3 code implementations • ICCV 2021 • Zihan Xu, Mingbao Lin, Jianzhuang Liu, Jie Chen, Ling Shao, Yue Gao, Yonghong Tian, Rongrong Ji
We prove that reviving the "dead weights" by ReCU can result in a smaller quantization error.
no code implementations • 22 Mar 2021 • Yawen Huang, Feng Zheng, Danyang Wang, Weilin Huang, Matthew R. Scott, Ling Shao
Recent advances in neuroscience have highlighted the effectiveness of multi-modal medical data for investigating certain pathologies and understanding human cognition.
1 code implementation • CVPR 2021 • Yichao Yan, Jinpeng Li, Jie Qin, Song Bai, Shengcai Liao, Li Liu, Fan Zhu, Ling Shao
Person search aims to simultaneously localize and identify a query person from realistic, uncropped images, which can be regarded as the unified task of pedestrian detection and person re-identification (re-id).
Ranked #10 on Person Search on CUHK-SYSU
no code implementations • 19 Mar 2021 • Tom van Sonsbeek, XianTong Zhen, Marcel Worring, Ling Shao
It is challenging to incorporate this information into disease classification due to the high reliance on clinician input in EHRs, limiting the possibility for automated diagnosis.
1 code implementation • CVPR 2021 • Qi Fan, Deng-Ping Fan, Huazhu Fu, Chi Keung Tang, Ling Shao, Yu-Wing Tai
We present a novel group collaborative learning framework (GCoNet) capable of detecting co-salient objects in real time (16ms), by simultaneously mining consensus representations at group level based on the two necessary criteria: 1) intra-group compactness to better formulate the consistency among co-salient objects by capturing their inherent shared attributes using our novel group affinity module; 2) inter-group separability to effectively suppress the influence of noisy objects on the output by introducing our new group collaborating module conditioning the inconsistent consensus.
Ranked #5 on Co-Salient Object Detection on CoCA
no code implementations • 26 Feb 2021 • Yi Zhou, Lei Huang, Tianfei Zhou, Ling Shao
For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming.
9 code implementations • ICCV 2021 • Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, Ling Shao
Unlike the recently-proposed Transformer model (e. g., ViT) that is specially designed for image classification, we propose Pyramid Vision Transformer~(PVT), which overcomes the difficulties of porting Transformer to various dense prediction tasks.
Ranked #5 on Semantic Segmentation on SynPASS
1 code implementation • 20 Feb 2021 • Deng-Ping Fan, Ge-Peng Ji, Ming-Ming Cheng, Ling Shao
We present the first systematic study on concealed object detection (COD), which aims to identify objects that are "perfectly" embedded in their background.
Ranked #5 on Camouflaged Object Segmentation on CHAMELEON
Camouflaged Object Segmentation Dichotomous Image Segmentation +2
1 code implementation • 20 Feb 2021 • Fangneng Zhan, Yingchen Yu, Changgong Zhang, Rongliang Wu, WenBo Hu, Shijian Lu, Feiying Ma, Xuansong Xie, Ling Shao
This paper presents Geometric Mover's Light (GMLight), a lighting estimation framework that employs a regression network and a generative projector for effective illumination estimation.
no code implementations • 16 Feb 2021 • Boulbaba Ben Amor, Sylvain Arguillère, Ling Shao
In deformable registration, the geometric framework - large deformation diffeomorphic metric mapping or LDDMM, in short - has inspired numerous techniques for comparing, deforming, averaging and analyzing shapes or images.
2 code implementations • 16 Feb 2021 • Mingbao Lin, Rongrong Ji, Zihan Xu, Baochang Zhang, Fei Chao, Chia-Wen Lin, Ling Shao
In this paper, we show that our weight binarization provides an analytical solution by encoding high-magnitude weights into +1s, and 0s otherwise.
8 code implementations • CVPR 2021 • Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, Ling Shao
At each stage, we introduce a novel per-pixel adaptive design that leverages in-situ supervised attention to reweight the local features.
Ranked #3 on Spectral Reconstruction on ARAD-1K
no code implementations • 3 Feb 2021 • Liangxi Liu, Xi Jiang, Feng Zheng, Hong Chen, Guo-Jun Qi, Heng Huang, Ling Shao
On the client side, a prior loss that uses the global posterior probabilistic parameters delivered from the server is designed to guide the local training.
1 code implementation • 27 Jan 2021 • Akshita Gupta, Sanath Narayan, Salman Khan, Fahad Shahbaz Khan, Ling Shao, Joost Van de Weijer
Nevertheless, computing reliable attention maps for unseen classes during inference in a multi-label setting is still a challenge.
Ranked #8 on Multi-label zero-shot learning on NUS-WIDE
3 code implementations • 19 Jan 2021 • Mingchen Zhuge, Deng-Ping Fan, Nian Liu, Dingwen Zhang, Dong Xu, Ling Shao
We define the concept of integrity at both a micro and macro level.
5 code implementations • 12 Jan 2021 • Xuebin Qin, Deng-Ping Fan, Chenyang Huang, Cyril Diagne, Zichen Zhang, Adrià Cabeza Sant'Anna, Albert Suàrez, Martin Jagersand, Ling Shao
In this paper, we propose a simple yet powerful Boundary-Aware Segmentation Network (BASNet), which comprises a predict-refine architecture and a hybrid loss, for highly accurate image segmentation.
no code implementations • 4 Jan 2021 • Aditya Arora, Muhammad Haris, Syed Waqas Zamir, Munawar Hayat, Fahad Shahbaz Khan, Ling Shao, Ming-Hsuan Yang
These contexts can be crucial towards inferring several image enhancement tasks, e. g., local and global contrast, brightness and color corrections; which requires cues from both local and global spatial extent.
no code implementations • ICCV 2021 • Yi Zhou, Lei Huang, Tao Zhou, Huazhu Fu, Ling Shao
Second, the progressive report decoder consists of a sentence decoder and a word decoder, where we propose image-sentence matching and description accuracy losses to constrain the visual-textual semantic consistency.
no code implementations • 1 Jan 2021 • Jiayi Shen, XianTong Zhen, Marcel Worring, Ling Shao
Multi-task learning aims to improve the overall performance of a set of tasks by leveraging their relatedness.
no code implementations • ICLR 2021 • Yingjun Du, XianTong Zhen, Ling Shao, Cees G. M. Snoek
Batch normalization plays a crucial role when training deep neural networks.
no code implementations • 1 Jan 2021 • Zehao Xiao, Jiayi Shen, XianTong Zhen, Ling Shao, Cees G. M. Snoek
In the probabilistic modeling framework, we introduce a domain-invariant principle to explore invariance across domains in a unified way.
no code implementations • ICCV 2021 • Guo-Sen Xie, Huan Xiong, Jie Liu, Yazhou Yao, Ling Shao
Specifically, we first generate N pairs (key and value) of multi-resolution query features guided by the support feature and its mask.
no code implementations • ICCV 2021 • Yi Zhou, Lei Huang, Tao Zhou, Ling Shao
A category-invariant cross-domain transfer (CCT) method is proposed to address this single-to-multiple extension.
no code implementations • ICCV 2021 • Nian Liu, Wangbo Zhao, Dingwen Zhang, Junwei Han, Ling Shao
In this paper, we model the information fusion within focal stack via graph networks.
1 code implementation • ICCV 2021 • Sanath Narayan, Hisham Cholakkal, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, Ling Shao
The proposed formulation comprises a discriminative and a denoising loss term for enhancing temporal action localization.
Ranked #3 on Weakly Supervised Action Localization on THUMOS’14
1 code implementation • CVPR 2021 • Wencheng Han, Xingping Dong, Fahad Shahbaz Khan, Ling Shao, Jianbing Shen
We propose a learnable module, called the asymmetric convolution (ACM), which learns to better capture the semantic correlation information in offline training on large-scale data.
Ranked #22 on Visual Object Tracking on TrackingNet
1 code implementation • NeurIPS 2020 • Fang Zhao, Shengcai Liao, Kaihao Zhang, Ling Shao
This paper proposes a human parsing based texture transfer model via cross-view consistency learning to generate the texture of 3D human body from a single image.
1 code implementation • 24 Nov 2020 • Wenhao Wang, Shengcai Liao, Fang Zhao, Cuicui Kang, Ling Shao
In this way, human annotations are no longer required, and it is scalable to large and diverse real-world datasets.
Generalizable Person Re-identification Unsupervised Domain Adaptation
1 code implementation • 17 Nov 2020 • Shaojie Li, Mingbao Lin, Yan Wang, Fei Chao, Ling Shao, Rongrong Ji
The latter simultaneously distills informative attention maps from both the generator and discriminator of a pre-trained model to the searched generator, effectively stabilizing the adversarial training of our light-weight model.
no code implementations • 11 Nov 2020 • Shidong Wang, Yi Ren, Gerard Parr, Yu Guan, Ling Shao
In this article, we propose a novel invariant deep compressible covariance pooling (IDCCP) to solve nuisance variations in aerial scene categorization.
1 code implementation • NeurIPS 2020 • XianTong Zhen, Yingjun Du, Huan Xiong, Qiang Qiu, Cees G. M. Snoek, Ling Shao
The variational semantic memory accrues and stores semantic information for the probabilistic inference of class prototypes in a hierarchical Bayesian framework.
1 code implementation • 12 Oct 2020 • Nian Liu, Ni Zhang, Ling Shao, Junwei Han
Early fusion and the result fusion schemes fuse RGB and depth information at the input and output stages, respectively, hence incur the problem of distribution gap or information loss.
2 code implementations • 1 Oct 2020 • Jiale Cao, Yanwei Pang, Jin Xie, Fahad Shahbaz Khan, Ling Shao
In addition to single-spectral pedestrian detection, we also review multi-spectral pedestrian detection, which provides more robust features for illumination variance.
1 code implementation • CVPR 2021 • Lei Huang, Yi Zhou, Li Liu, Fan Zhu, Ling Shao
Results show that GW consistently improves the performance of different architectures, with absolute gains of $1. 02\%$ $\sim$ $1. 49\%$ in top-1 accuracy on ImageNet and $1. 82\%$ $\sim$ $3. 21\%$ in bounding box AP on COCO.
no code implementations • 27 Sep 2020 • Lei Huang, Jie Qin, Yi Zhou, Fan Zhu, Li Liu, Ling Shao
Normalization techniques are essential for accelerating the training and improving the generalization of deep neural networks (DNNs), and have successfully been used in various applications.
no code implementations • 23 Sep 2020 • Ping Li, Qinghao Ye, Luming Zhang, Li Yuan, Xianghua Xu, Ling Shao
In this paper, we propose an efficient convolutional neural network architecture for video SUMmarization via Global Diverse Attention called SUM-GDA, which adapts attention mechanism in a global perspective to consider pairwise temporal relations of video frames.
no code implementations • 22 Aug 2020 • Yi Zhou, Boyang Wang, Lei Huang, Shanshan Cui, Ling Shao
This dataset has 1, 842 images with pixel-level DR-related lesion annotations, and 1, 000 images with image-level labels graded by six board-certified ophthalmologists with intra-rater consistency.
no code implementations • 5 Aug 2020 • Dwarikanath Mahapatra, Behzad Bozorgtabar, Jean-Philippe Thiran, Ling Shao
Although generative adversarial network (GAN) based style transfer is state of the art in histopathology color-stain normalization, they do not explicitly integrate structural information of tissues.
9 code implementations • 1 Aug 2020 • Tao Zhou, Deng-Ping Fan, Ming-Ming Cheng, Jianbing Shen, Ling Shao
Further, considering that the light field can also provide depth maps, we review SOD models and popular benchmark datasets from this domain as well.
1 code implementation • ECCV 2020 • Jiale Cao, Rao Muhammad Anwer, Hisham Cholakkal, Fahad Shahbaz Khan, Yanwei Pang, Ling Shao
In terms of real-time capabilities, SipMask outperforms YOLACT with an absolute gain of 3. 0% (mask AP) under similar settings, while operating at comparable speed on a Titan Xp.
Ranked #12 on Real-time Instance Segmentation on MSCOCO
5 code implementations • ECCV 2020 • Mang Ye, Jianbing Shen, David J. Crandall, Ling Shao, Jiebo Luo
In this paper, we propose a novel dynamic dual-attentive aggregation (DDAG) learning method by mining both intra-modality part-level and cross-modality graph-level contextual cues for VI-ReID.
no code implementations • ECCV 2020 • Ying-Jun Du, Jun Xu, Huan Xiong, Qiang Qiu, Xian-Tong Zhen, Cees G. M. Snoek, Ling Shao
Domain generalization models learn to generalize to previously unseen domains, but suffer from prediction uncertainty and domain shift.
2 code implementations • 6 Jul 2020 • Yingjie Zhai, Deng-Ping Fan, Jufeng Yang, Ali Borji, Ling Shao, Junwei Han, Liang Wang
In particular, first, we propose to regroup the multi-level features into teacher and student features using a bifurcated backbone strategy (BBS).
Ranked #2 on RGB-D Salient Object Detection on RGBD135
1 code implementation • 23 Jun 2020 • Yanan Wang, Shengcai Liao, Ling Shao
To address this, we propose to automatically synthesize a large-scale person re-identification dataset following a set-up similar to real surveillance but with virtual environments, and then use the synthesized person images to train a generalizable person re-identification model.
Domain Generalization Generalizable Person Re-identification +1
3 code implementations • 20 Jun 2020 • Ionut Cosmin Duta, Li Liu, Fan Zhu, Ling Shao
This work introduces pyramidal convolution (PyConv), which is capable of processing the input at multiple filter scales.
Ranked #69 on Semantic Segmentation on ADE20K val
4 code implementations • 13 Jun 2020 • Deng-Ping Fan, Ge-Peng Ji, Tao Zhou, Geng Chen, Huazhu Fu, Jianbing Shen, Ling Shao
To address these challenges, we propose a parallel reverse attention network (PraNet) for accurate polyp segmentation in colonoscopy images.
Ranked #7 on Video Polyp Segmentation on SUN-SEG-Easy (Unseen)
1 code implementation • 11 Jun 2020 • Wenhao Wang, Fang Zhao, Shengcai Liao, Ling Shao
This paper proposes a novel light-weight module, the Attentive WaveBlock (AWB), which can be integrated into the dual networks of mutual learning to enhance the complementarity and further depress noise in the pseudo-labels.
Ranked #2 on Unsupervised Domain Adaptation on Duke to MSMT
1 code implementation • ICML 2020 • Xiantong Zhen, Haoliang Sun, Ying-Jun Du, Jun Xu, Yilong Yin, Ling Shao, Cees Snoek
We propose meta variational random features (MetaVRF) to learn adaptive kernels for the base-learner, which is developed in a latent variable model by treating the random feature basis as the latent variable.
1 code implementation • 1 Jun 2020 • Tao Zhou, Huazhu Fu, Yu Zhang, Changqing Zhang, Xiankai Lu, Jianbing Shen, Ling Shao
Then, we use a modality-specific network to extract implicit and high-level features from different MR scans.
1 code implementation • 12 May 2020 • Ziyi Shen, Huazhu Fu, Jianbing Shen, Ling Shao
Retinal fundus images are widely used for the clinical screening and diagnosis of eye diseases.
1 code implementation • 23 Apr 2020 • Ying-Jun Du, Jun Xu, Xian-Tong Zhen, Ming-Ming Cheng, Ling Shao
In this paper, we propose a Conditional Variational Image Deraining (CVID) network for better deraining performance, leveraging the exclusive generative ability of Conditional Variational Auto-Encoder (CVAE) on providing diverse predictions for the rainy image.
3 code implementations • 22 Apr 2020 • Deng-Ping Fan, Tao Zhou, Ge-Peng Ji, Yi Zhou, Geng Chen, Huazhu Fu, Jianbing Shen, Ling Shao
Coronavirus Disease 2019 (COVID-19) spread globally in early 2020, causing the world to face an existential health crisis.
2 code implementations • 10 Apr 2020 • Ionut Cosmin Duta, Li Liu, Fan Zhu, Ling Shao
We successfully train a 404-layer deep CNN on the ImageNet dataset and a 3002-layer network on CIFAR-10 and CIFAR-100, while the baseline is not able to converge at such extreme depths.
no code implementations • 10 Apr 2020 • Jiale Li, Shujie Luo, Ziqi Zhu, Hang Dai, Andrey S. Krylov, Yong Ding, Ling Shao
In order to obtain a more accurate IoU prediction, we propose a 3D IoU-Net with IoU sensitive feature learning and an IoU alignment operation.
no code implementations • 4 Apr 2020 • Ahmed H. Shahin, Prateek Munjal, Ling Shao, Shadab Khan
We propose a novel approach for effectively encoding the user input from extreme points and corrective clicks, in a novel and scalable manner that allows the network to work with a variable number of clicks, including corrective clicks for output refinement.
1 code implementation • CVPR 2020 • Lei Huang, Li Liu, Fan Zhu, Diwen Wan, Zehuan Yuan, Bo Li, Ling Shao
Orthogonality is widely used for training deep neural networks (DNNs) due to its ability to maintain all singular values of the Jacobian close to 1 and reduce redundancy in representation.
no code implementations • CVPR 2020 • Dwarikanath Mahapatra, Behzad Bozorgtabar, Jean-Philippe Thiran, Ling Shao
The proposed method outperforms state-of-the-art segmentation methods on the public RETOUCH dataset having images captured from different acquisition procedures.
1 code implementation • ICCV 2021 • Jie Hu, Liujuan Cao, Qixiang Ye, Tong Tong, Shengchuan Zhang, Ke Li, Feiyue Huang, Rongrong Ji, Ling Shao
Based on the experimental results, we present three new findings that provide fresh insights into the inner logic of DNNs.
1 code implementation • CVPR 2020 • Lei Huang, Lei Zhao, Yi Zhou, Fan Zhu, Li Liu, Ling Shao
Our work originates from the observation that while various whitening transformations equivalently improve the conditioning, they show significantly different behaviors in discriminative scenarios and training Generative Adversarial Networks (GANs).
1 code implementation • CVPR 2021 • Irtiza Hasan, Shengcai Liao, Jinpeng Li, Saad Ullah Akram, Ling Shao
Furthermore, we illustrate that diverse and dense datasets, collected by crawling the web, serve to be an efficient source of pre-training for pedestrian detection.
Ranked #3 on Pedestrian Detection on CityPersons (using extra training data)
1 code implementation • ECCV 2020 • Sanath Narayan, Akshita Gupta, Fahad Shahbaz Khan, Cees G. M. Snoek, Ling Shao
We propose to enforce semantic consistency at all stages of (generalized) zero-shot learning: training, feature synthesis and classification.
Ranked #2 on Generalized Zero-Shot Learning on CUB-200-2011
8 code implementations • CVPR 2020 • Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, Ling Shao
This is mainly because the AWGN is not adequate for modeling the real camera noise which is signal-dependent and heavily transformed by the camera imaging pipeline.
Ranked #10 on Image Denoising on DND (using extra training data)
12 code implementations • ECCV 2020 • Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, Ling Shao
With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in surveillance, computational photography, medical imaging, and remote sensing.
Ranked #5 on Spectral Reconstruction on ARAD-1K
1 code implementation • CVPR 2020 • Wenguan Wang, Hailong Zhu, Jifeng Dai, Yanwei Pang, Jianbing Shen, Ling Shao
As human bodies are underlying hierarchically structured, how to model human structures is the central theme in this task.
1 code implementation • 9 Mar 2020 • Tianfei Zhou, Shunzhou Wang, Yi Zhou, Yazhou Yao, Jianwu Li, Ling Shao
In this paper, we present a novel Motion-Attentive Transition Network (MATNet) for zero-shot video object segmentation, which provides a new way of leveraging motion information to reinforce spatio-temporal object representation.
Ranked #9 on Unsupervised Video Object Segmentation on FBMS test
2 code implementations • 8 Mar 2020 • Haibo Jin, Shengcai Liao, Ling Shao
The proposed model is equipped with a novel detection head based on heatmap regression, which conducts score and offset predictions simultaneously on low-resolution feature maps.
Ranked #4 on Face Alignment on COFW
2 code implementations • CVPR 2020 • Yuming Shen, Jie Qin, Jiaxin Chen, Mengyang Yu, Li Liu, Fan Zhu, Fumin Shen, Ling Shao
One bottleneck (i. e., binary codes) conveys the high-level intrinsic data structure captured by the code-driven graph to the other (i. e., continuous variables for low-level detail information), which in turn propagates the updated network feedback for the encoder to learn more discriminative binary codes.
no code implementations • 26 Feb 2020 • Jilin Hu, Jianbing Shen, Bin Yang, Ling Shao
Graph convolutional neural networks~(GCNs) have recently demonstrated promising results on graph-based semi-supervised classification, but little work has been done to explore their theoretical properties.
no code implementations • ECCV 2020 • Lei Huang, Jie Qin, Li Liu, Fan Zhu, Ling Shao
To this end, we propose layer-wise conditioning analysis, which explores the optimization landscape with respect to each layer independently.
2 code implementations • CVPR 2020 • Mingbao Lin, Rongrong Ji, Yan Wang, Yichen Zhang, Baochang Zhang, Yonghong Tian, Ling Shao
The principle behind our pruning is that low-rank feature maps contain less information, and thus pruned results can be easily reproduced.
2 code implementations • 11 Feb 2020 • Tao Zhou, Huazhu Fu, Geng Chen, Jianbing Shen, Ling Shao
Medical image synthesis has been proposed as an effective solution to this, where any missing modalities are synthesized from the existing ones.
no code implementations • 25 Jan 2020 • Jin Xie, Yanwei Pang, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan, Ling Shao
On the heavy occluded (\textbf{HO}) set of CityPerosns test set, our PSC-Net obtains an absolute gain of 4. 0\% in terms of log-average miss rate over the state-of-the-art with same backbone, input scale and without using additional VBB supervision.
1 code implementation • ICCV 2019 • Wenguan Wang, Xiankai Lu, Jianbing Shen, David Crandall, Ling Shao
Through parametric message passing, AGNN is able to efficiently capture and mine much richer and higher-order relations between video frames, thus enabling a more complete understanding of video content and more accurate foreground estimation.
1 code implementation • ICCV 2019 • Wenguan Wang, Zhijie Zhang, Siyuan Qi, Jianbing Shen, Yanwei Pang, Ling Shao
The bottom-up and top-down inferences explicitly model the compositional and decompositional relations in human bodies, respectively.
1 code implementation • ICCV 2019 • Ziyi Shen, Wenguan Wang, Xiankai Lu, Jianbing Shen, Haibin Ling, Tingfa Xu, Ling Shao
This paper proposes a human-aware deblurring model that disentangles the motion blur between foreground (FG) humans and background (BG).
1 code implementation • CVPR 2019 • Xiankai Lu, Wenguan Wang, Chao Ma, Jianbing Shen, Ling Shao, Fatih Porikli
We introduce a novel network, called CO-attention Siamese Network (COSNet), to address the unsupervised video object segmentation task from a holistic view.
Semantic Segmentation Unsupervised Video Object Segmentation +2
no code implementations • CVPR 2020 • Yazhao Li, Yanwei Pang, Jianbing Shen, Jiale Cao, Ling Shao
With this observation, we propose a new Neighbor Erasing and Transferring (NET) mechanism to reconfigure the pyramid features and explore scale-aware features.
5 code implementations • 13 Jan 2020 • Mang Ye, Jianbing Shen, Gaojie Lin, Tao Xiang, Ling Shao, Steven C. H. Hoi
The widely studied closed-world setting is usually applied under various research-oriented assumptions, and has achieved inspiring success using deep learning techniques on a number of datasets.
Ranked #1 on Cross-Modal Person Re-Identification on RegDB-C
no code implementations • 14 Dec 2019 • Guolei Sun, Hisham Cholakkal, Salman Khan, Fahad Shahbaz Khan, Ling Shao
The main requisite for fine-grained recognition task is to focus on subtle discriminative details that make the subordinate classes different from each other.
Ranked #16 on Fine-Grained Image Classification on Stanford Dogs
1 code implementation • 13 Dec 2019 • Hisham Cholakkal, Guolei Sun, Salman Khan, Fahad Shahbaz Khan, Ling Shao, Luc van Gool
Our RLC framework further reduces the annotation cost arising from large numbers of object categories in a dataset by only using lower-count supervision for a subset of categories and class-labels for the remaining ones.
Image Classification Image-level Supervised Instance Segmentation +3
no code implementations • 10 Dec 2019 • Yi Zhou, Boyang Wang, Xiaodong He, Shanshan Cui, Ling Shao
In this paper, we propose a diabetic retinopathy generative adversarial network (DR-GAN) to synthesize high-resolution fundus images which can be manipulated with arbitrary grading and lesion information.
no code implementations • NeurIPS 2019 • Lizhong Ding, Mengyang Yu, Li Liu, Fan Zhu, Yong liu, Yu Li, Ling Shao
DEAN can be interpreted as a GOF game between two generative networks, where one explicit generative network learns an energy-based distribution that fits the real data, and the other implicit generative network is trained by minimizing a GOF test statistic between the energy-based distribution and the generated data, such that the underlying distribution of the generated data is close to the energy-based distribution.
1 code implementation • NeurIPS 2019 • Jathushan Rajasegaran, Munawar Hayat, Salman H. Khan, Fahad Shahbaz Khan, Ling Shao
In order to maintain an equilibrium between previous and newly acquired knowledge, we propose a simple controller to dynamically balance the model plasticity.
Ranked #7 on Continual Learning on F-CelebA (10 tasks)
no code implementations • 1 Dec 2019 • Biao Qian, Yang Wang, Zhao Zhang, Richang Hong, Meng Wang, Ling Shao
We intuitively find that M$^2$Net can essentially promote the diversity of the inference path (selected blocks subset) selection, so as to enhance the recognition accuracy.
no code implementations • 10 Nov 2019 • Jianjun Lei, Yuxin Song, Bo Peng, Zhanyu Ma, Ling Shao, Yi-Zhe Song
How to align abstract sketches and natural images into a common high-level semantic space remains a key problem in SBIR.
no code implementations • ICCV 2019 • Tiancai Wang, Rao Muhammad Anwer, Muhammad Haris Khan, Fahad Shahbaz Khan, Yanwei Pang, Ling Shao, Jorma Laaksonen
Our approach outperforms the state-of-the-art on all datasets.
1 code implementation • ICCV 2019 • Yanwei Pang, Jin Xie, Muhammad Haris Khan, Rao Muhammad Anwer, Fahad Shahbaz Khan, Ling Shao
Our approach obtains an absolute gain of 9. 5% in log-average miss rate, compared to the best reported results on the heavily occluded (HO) pedestrian set of CityPersons test set.
no code implementations • 16 Sep 2019 • Huan Xiong, Mengyang Yu, Li Liu, Fan Zhu, Fumin Shen, Ling Shao
Binary optimization, a representative subclass of discrete optimization, plays an important role in mathematical optimization and has various applications in computer vision and machine learning.
1 code implementation • CVPR 2020 • Muhammad Haris Khan, John McDonagh, Salman Khan, Muhammad Shahabuddin, Aditya Arora, Fahad Shahbaz Khan, Ling Shao, Georgios Tzimiropoulos
Several studies show that animal needs are often expressed through their faces.
1 code implementation • ICCV 2019 • Sanath Narayan, Hisham Cholakkal, Fahad Shahbaz Khan, Ling Shao
Our joint formulation has three terms: a classification term to ensure the separability of learned action features, an adapted multi-label center loss term to enhance the action feature discriminability and a counting loss term to delineate adjacent action sequences, leading to improved localization.
Ranked #1 on Action Classification on THUMOS'14
Action Classification Weakly Supervised Action Localization +2
2 code implementations • ICCV 2019 • Ziqin Wang, Jun Xu, Li Liu, Fan Zhu, Ling Shao
Specifically, to integrate the insights of matching based and propagation based methods, we employ an encoder-decoder framework to learn pixel-level similarity and segmentation in an end-to-end manner.
no code implementations • 7 Aug 2019 • Yuan Zhou, Bingzhang Hu, and Jun He, Yu Guan, Ling Shao
Age synthesis methods typically take a single image as input and use a specific number to control the age of the generated image.
1 code implementation • 25 Jul 2019 • Zhijie Zhang, Huazhu Fu, Hang Dai, Jianbing Shen, Yanwei Pang, Ling Shao
Segmentation is a fundamental task in medical image analysis.
Ranked #1 on Optic Disc Segmentation on REFUGE
no code implementations • 12 Jul 2019 • Chun-Mei Feng, Kai Wang, Shijian Lu, Yong Xu, Heng Kong, Ling Shao
The deep sub-network learns from the residuals of the high-frequency image information, where multiple residual blocks are cascaded to magnify the MRI images at the last network layer.
4 code implementations • 10 Jul 2019 • Huazhu Fu, Boyang Wang, Jianbing Shen, Shanshan Cui, Yanwu Xu, Jiang Liu, Ling Shao
Retinal image quality assessment (RIQA) is essential for controlling the quality of retinal imaging and guaranteeing the reliability of diagnoses by ophthalmologists or automated analysis systems.
no code implementations • 20 Jun 2019 • Qiuxia Lai, Salman Khan, Yongwei Nie, Jianbing Shen, Hanqiu Sun, Ling Shao
With three example computer vision tasks, diverse representative backbones, and famous architectures, corresponding real human gaze data, and systematically conducted large-scale quantitative studies, we quantify the consistency between artificial attention and human visual attention and offer novel insights into existing artificial attention mechanisms by giving preliminary answers to several key questions related to human and artificial attention mechanisms.
1 code implementation • 17 Jun 2019 • Jun Xu, Yuan Huang, Ming-Ming Cheng, Li Liu, Fan Zhu, Zhou Xu, Ling Shao
A simple but useful observation on our NAC is: as long as the noise is weak, it is feasible to learn a self-supervised network only with the corrupted image, approximating the optimal parameters of a supervised network learned with pairs of noisy and clean images.