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.
no code implementations • ECCV 2020 • Sihui Luo, Wenwen Pan, Xinchao Wang, Dazhou Wang, Haihong Tang, Mingli Song
To this end, we propose a self-coordinate knowledge amalgamation network (SOKA-Net) for learning the multi-talent student model.
1 code implementation • 20 Mar 2023 • Chenxin Xu, Robby T. Tan, Yuhong Tan, Siheng Chen, Yu Guang Wang, Xinchao Wang, Yanfeng Wang
In motion prediction tasks, maintaining motion equivariance under Euclidean geometric transformations and invariance of agent interaction is a critical and fundamental principle.
Ranked #1 on
Human Pose Forecasting
on Human3.6M
1 code implementation • 19 Mar 2023 • Jingwen Ye, Songhua Liu, Xinchao Wang
Unlike prior methods that update all or at least part of the parameters in the target network throughout the knowledge transfer process, PNC conducts partial parametric "cloning" from a source network and then injects the cloned module to the target, without modifying its parameters.
1 code implementation • 30 Jan 2023 • Gongfan Fang, Xinyin Ma, Mingli Song, Michael Bi Mi, Xinchao Wang
Structural pruning enables model acceleration by removing structurally-grouped parameters from neural networks.
1 code implementation • 17 Jan 2023 • Ruonan Yu, Songhua Liu, Xinchao Wang
Recent success of deep learning is largely attributed to the sheer amount of data used for training deep neural networks. Despite the unprecedented success, the massive data, unfortunately, significantly increases the burden on storage and transmission and further gives rise to a cumbersome model training process.
no code implementations • 27 Nov 2022 • Xingyi Yang, Daquan Zhou, Jiashi Feng, Xinchao Wang
Despite the recent visually-pleasing results achieved, the massive computational cost has been a long-standing flaw for diffusion probabilistic models (DPMs), which, in turn, greatly limits their applications on resource-limited platforms.
1 code implementation • 26 Nov 2022 • Jianfeng Zhang, Zihang Jiang, Dingdong Yang, Hongyi Xu, Yichun Shi, Guoxian Song, Zhongcong Xu, Xinchao Wang, Jiashi Feng
Specifically, we decompose the generative 3D human synthesis into pose-guided mapping and canonical representation with predefined human pose and shape, such that the canonical representation can be explicitly driven to different poses and shapes with the guidance of a 3D parametric human model SMPL.
1 code implementation • 18 Nov 2022 • Tao Yu, Zhihe Lu, Xin Jin, Zhibo Chen, Xinchao Wang
Large-scale vision-language models (VLMs) pre-trained on billion-level data have learned general visual representations and broad visual concepts.
1 code implementation • NIPS 2022 • Songhua Liu, Kai Wang, Xingyi Yang, Jingwen Ye, Xinchao Wang
In this paper, we study dataset distillation (DD), from a novel perspective and introduce a \emph{dataset factorization} approach, termed \emph{HaBa}, which is a plug-and-play strategy portable to any existing DD baseline.
2 code implementations • 30 Oct 2022 • Songhua Liu, Kai Wang, Xingyi Yang, Jingwen Ye, Xinchao Wang
In this paper, we study \xw{dataset distillation (DD)}, from a novel perspective and introduce a \emph{dataset factorization} approach, termed \emph{HaBa}, which is a plug-and-play strategy portable to any existing DD baseline.
5 code implementations • 24 Oct 2022 • Weihao Yu, Chenyang Si, Pan Zhou, Mi Luo, Yichen Zhou, Jiashi Feng, Shuicheng Yan, Xinchao Wang
By simply applying depthwise separable convolutions as token mixer in the bottom stages and vanilla self-attention in the top stages, the resulting model CAFormer sets a new record on ImageNet-1K: it achieves an accuracy of 85. 5% at 224x224 resolution, under normal supervised training without external data or distillation.
Ranked #57 on
Image Classification
on ImageNet
(using extra training data)
1 code implementation • 24 Oct 2022 • Xingyi Yang, Daquan Zhou, Songhua Liu, Jingwen Ye, Xinchao Wang
Given a collection of heterogeneous models pre-trained from distinct sources and with diverse architectures, the goal of DeRy, as its name implies, is to first dissect each model into distinctive building blocks, and then selectively reassemble the derived blocks to produce customized networks under both the hardware resource and performance constraints.
no code implementations • 24 Oct 2022 • Kaixin Wang, Kuangqi Zhou, Jiashi Feng, Bryan Hooi, Xinchao Wang
In Reinforcement Learning (RL), Laplacian Representation (LapRep) is a task-agnostic state representation that encodes the geometry of the environment.
1 code implementation • 17 Oct 2022 • Dongze Lian, Daquan Zhou, Jiashi Feng, Xinchao Wang
With the proposed SSF, our model obtains 2. 46% (90. 72% vs. 88. 54%) and 11. 48% (73. 10% vs. 65. 57%) performance improvement on FGVC and VTAB-1k in terms of Top-1 accuracy compared to the full fine-tuning but only fine-tuning about 0. 3M parameters.
1 code implementation • 10 Oct 2022 • Qu Yang, Jibin Wu, Malu Zhang, Yansong Chua, Xinchao Wang, Haizhou Li
The LTL rule follows the teacher-student learning approach by mimicking the intermediate feature representations of a pre-trained ANN.
1 code implementation • 9 Oct 2022 • Rang Meng, Xianfeng Li, WeiJie Chen, Shicai Yang, Jie Song, Xinchao Wang, Lei Zhang, Mingli Song, Di Xie, ShiLiang Pu
Under this guidance, a novel Attention Diversification framework is proposed, in which Intra-Model and Inter-Model Attention Diversification Regularization are collaborated to reassign appropriate attention to diverse task-related features.
no code implementations • 25 Aug 2022 • Yu Cheng, Yihao Ai, Bo wang, Xinchao Wang, Robby T. Tan
In multi-person 2D pose estimation, the bottom-up methods simultaneously predict poses for all persons, and unlike the top-down methods, do not rely on human detection.
1 code implementation • 1 Aug 2022 • Jianfeng Zhang, Zihang Jiang, Dingdong Yang, Hongyi Xu, Yichun Shi, Guoxian Song, Zhongcong Xu, Xinchao Wang, Jiashi Feng
Unsupervised generation of clothed virtual humans with various appearance and animatable poses is important for creating 3D human avatars and other AR/VR applications.
no code implementations • 27 Jul 2022 • Donglin Xie, Ruonan Yu, Gongfan Fang, Jie Song, Zunlei Feng, Xinchao Wang, Li Sun, Mingli Song
The goal of FedSA is to train a student model for a new task with the help of several decentralized teachers, whose pre-training tasks and data are different and agnostic.
1 code implementation • 24 Jul 2022 • Gaoang Wang, Yibing Zhan, Xinchao Wang, Mingli Song, Klara Nahrstedt
Anomaly detection aims at identifying deviant samples from the normal data distribution.
no code implementations • 24 Jul 2022 • Yongcheng Jing, Yining Mao, Yiding Yang, Yibing Zhan, Mingli Song, Xinchao Wang, DaCheng Tao
To this end, we develop an elaborated GNN model with content and style local patches as the graph vertices.
no code implementations • 17 Jul 2022 • Jingwen Ye, Yifang Fu, Jie Song, Xingyi Yang, Songhua Liu, Xin Jin, Mingli Song, Xinchao Wang
Life-long learning aims at learning a sequence of tasks without forgetting the previously acquired knowledge.
1 code implementation • 13 Jul 2022 • Songhua Liu, Jingwen Ye, Sucheng Ren, Xinchao Wang
Prior approaches, despite the promising results, have relied on either estimating dense attention to compute per-point matching, which is limited to only coarse scales due to the quadratic memory cost, or fixing the number of correspondences to achieve linear complexity, which lacks flexibility.
1 code implementation • 4 Jul 2022 • Xingyi Yang, Jingwen Ye, Xinchao Wang
The core idea of KF lies in the modularization and assemblability of knowledge: given a pretrained network model as input, KF aims to decompose it into several factor networks, each of which handles only a dedicated task and maintains task-specific knowledge factorized from the source network.
1 code implementation • CVPR 2022 • Rang Meng, WeiJie Chen, Shicai Yang, Jie Song, Luojun Lin, Di Xie, ShiLiang Pu, Xinchao Wang, Mingli Song, Yueting Zhuang
In this paper, we introduce a simple framework, Slimmable Domain Adaptation, to improve cross-domain generalization with a weight-sharing model bank, from which models of different capacities can be sampled to accommodate different accuracy-efficiency trade-offs.
1 code implementation • 13 Jun 2022 • Meilin Chen, WeiJie Chen, Shicai Yang, Jie Song, Xinchao Wang, Lei Zhang, Yunfeng Yan, Donglian Qi, Yueting Zhuang, Di Xie, ShiLiang Pu
In addition, we conduct anchor adaptation in parallel with localization adaptation, since anchor can be regarded as a learnable parameter.
2 code implementations • 25 May 2022 • Chenyang Si, Weihao Yu, Pan Zhou, Yichen Zhou, Xinchao Wang, Shuicheng Yan
Recent studies show that Transformer has strong capability of building long-range dependencies, yet is incompetent in capturing high frequencies that predominantly convey local information.
1 code implementation • 23 May 2022 • Kai Wang, Bo Zhao, Xiangyu Peng, Zheng Zhu, Jiankang Deng, Xinchao Wang, Hakan Bilen, Yang You
Firstly, randomly masked face images are used to train the reconstruction module in FaceMAE.
no code implementations • 23 May 2022 • Kuangqi Zhou, Kaixin Wang, Jiashi Feng, Jian Tang, Tingyang Xu, Xinchao Wang
However, existing best deep AL methods are mostly developed for a single type of learning task (e. g., single-label classification), and hence may not perform well in molecular property prediction that involves various task types.
no code implementations • 16 May 2022 • Xinyin Ma, Xinchao Wang, Gongfan Fang, Yongliang Shen, Weiming Lu
Data-free knowledge distillation (DFKD) conducts knowledge distillation via eliminating the dependence of original training data, and has recently achieved impressive results in accelerating pre-trained language models.
1 code implementation • ACL 2022 • Jinming Zhao, Tenggan Zhang, Jingwen Hu, Yuchen Liu, Qin Jin, Xinchao Wang, Haizhou Li
In this work, we propose a Multi-modal Multi-scene Multi-label Emotional Dialogue dataset, M3ED, which contains 990 dyadic emotional dialogues from 56 different TV series, a total of 9, 082 turns and 24, 449 utterances.
1 code implementation • 30 Apr 2022 • Kai Wang, Xiangyu Peng, Shuo Yang, Jianfei Yang, Zheng Zhu, Xinchao Wang, Yang You
This paradigm, however, is prone to significant degeneration under heavy label noise, as the number of clean samples is too small for conventional methods to behave well.
1 code implementation • CVPR 2022 • Wangbo Zhao, Kai Wang, Xiangxiang Chu, Fuzhao Xue, Xinchao Wang, Yang You
Text-based video segmentation aims to segment the target object in a video based on a describing sentence.
Ranked #7 on
Referring Expression Segmentation
on A2D Sentences
Optical Flow Estimation
Referring Expression Segmentation
+2
1 code implementation • CVPR 2022 • Kehong Gong, Bingbing Li, Jianfeng Zhang, Tao Wang, Jing Huang, Michael Bi Mi, Jiashi Feng, Xinchao Wang
Existing self-supervised 3D human pose estimation schemes have largely relied on weak supervisions like consistency loss to guide the learning, which, inevitably, leads to inferior results in real-world scenarios with unseen poses.
Ranked #15 on
3D Human Pose Estimation
on MPI-INF-3DHP
1 code implementation • CVPR 2022 • Yujing Xue, Jiageng Mao, Minzhe Niu, Hang Xu, Michael Bi Mi, Wei zhang, Xiaogang Wang, Xinchao Wang
We further propose a lightweight scene-to-sequence decoder that can auto-regressively generate words conditioned on features from a 3D scene as well as cues from the preceding words.
2 code implementations • CVPR 2022 • Kai Wang, Bo Zhao, Xiangyu Peng, Zheng Zhu, Shuo Yang, Shuo Wang, Guan Huang, Hakan Bilen, Xinchao Wang, Yang You
Dataset condensation aims at reducing the network training effort through condensing a cumbersome training set into a compact synthetic one.
1 code implementation • CVPR 2022 • Peng Du, Jifeng Ning, Jiguang Cui, Shaoli Huang, Xinchao Wang, Jiaxin Wang
Further, an optimized GES energy term is presented to reasonably determine the weights of the sampling points on the geometric structure, and the term is added into the Global Similarity Prior (GSP) stitching model called GES-GSP to achieve a smooth transition between local alignment and geometric structure preservation.
no code implementations • 21 Dec 2021 • Jue Wang, Shaoli Huang, Xinchao Wang, DaCheng Tao
Conventional 3D human pose estimation relies on first detecting 2D body keypoints and then solving the 2D to 3D correspondence problem. Despite the promising results, this learning paradigm is highly dependent on the quality of the 2D keypoint detector, which is inevitably fragile to occlusions and out-of-image absences. In this paper, we propose a novel Pose Orientation Net (PONet) that is able to robustly estimate 3D pose by learning orientations only, hence bypassing the error-prone keypoint detector in the absence of image evidence.
Ranked #54 on
3D Human Pose Estimation
on MPI-INF-3DHP
1 code implementation • 12 Dec 2021 • Gongfan Fang, Kanya Mo, Xinchao Wang, Jie Song, Shitao Bei, Haofei Zhang, Mingli Song
At the heart of our approach is a novel strategy to reuse the shared common features in training data so as to synthesize different data instances.
no code implementations • 5 Dec 2021 • Jingwen Ye, Yining Mao, Jie Song, Xinchao Wang, Cheng Jin, Mingli Song
In other words, all users may employ a model in SDB for inference, but only authorized users get access to KD from the model.
1 code implementation • CVPR 2022 • Sucheng Ren, Daquan Zhou, Shengfeng He, Jiashi Feng, Xinchao Wang
This novel merging scheme enables the self-attention to learn relationships between objects with different sizes and simultaneously reduces the token numbers and the computational cost.
12 code implementations • CVPR 2022 • Weihao Yu, Mi Luo, Pan Zhou, Chenyang Si, Yichen Zhou, Xinchao Wang, Jiashi Feng, Shuicheng Yan
Based on this observation, we hypothesize that the general architecture of the Transformers, instead of the specific token mixer module, is more essential to the model's performance.
Ranked #9 on
Semantic Segmentation
on DensePASS
no code implementations • 19 Nov 2021 • Xin Jin, Tianyu He, Xu Shen, Tongliang Liu, Xinchao Wang, Jianqiang Huang, Zhibo Chen, Xian-Sheng Hua
Unsupervised Person Re-identification (U-ReID) with pseudo labeling recently reaches a competitive performance compared to fully-supervised ReID methods based on modern clustering algorithms.
1 code implementation • NeurIPS 2021 • Gongfan Fang, Yifan Bao, Jie Song, Xinchao Wang, Donglin Xie, Chengchao Shen, Mingli Song
Knowledge distillation~(KD) aims to craft a compact student model that imitates the behavior of a pre-trained teacher in a target domain.
no code implementations • 27 Oct 2021 • Jinming Zhao, Ruichen Li, Qin Jin, Xinchao Wang, Haizhou Li
Multimodal emotion recognition study is hindered by the lack of labelled corpora in terms of scale and diversity, due to the high annotation cost and label ambiguity.
no code implementations • 29 Sep 2021 • Xin Jin, Tianyu He, Xu Shen, Songhua Wu, Tongliang Liu, Xinchao Wang, Jianqiang Huang, Zhibo Chen, Xian-Sheng Hua
In this paper, we propose an embarrassing simple yet highly effective adversarial domain adaptation (ADA) method for effectively training models for alignment.
no code implementations • NeurIPS Workshop ImageNet_PPF 2021 • Dapeng Hu, Shipeng Yan, Qizhengqiu Lu, Lanqing Hong, Hailin Hu, Yifan Zhang, Zhenguo Li, Xinchao Wang, Jiashi Feng
Prior works on self-supervised pre-training focus on the joint training scenario, where massive unlabeled data are assumed to be given as input all at once, and only then is a learner trained.
no code implementations • ICCV 2021 • Yongcheng Jing, Yiding Yang, Xinchao Wang, Mingli Song, DaCheng Tao
In this paper, we study a novel meta aggregation scheme towards binarizing graph neural networks (GNNs).
no code implementations • 16 Aug 2021 • Lianbo Zhang, Shaoli Huang, Xinchao Wang, Wei Liu, DaCheng Tao
In this paper, we introduce a novel structure-aware feature generation scheme, termed as SA-GAN, to explicitly account for the topological structure in learning both the latent space and the generative networks.
no code implementations • 1 Aug 2021 • Lechao Cheng, Zunlei Feng, Xinchao Wang, Ya Jie Liu, Jie Lei, Mingli Song
In this paper, we introduce a novel Reference semantic segmentation Network (Ref-Net) to conduct visual boundary knowledge translation.
1 code implementation • 1 Aug 2021 • Zunlei Feng, Lechao Cheng, Xinchao Wang, Xiang Wang, Yajie Liu, Xiangtong Du, Mingli Song
To this end, we propose a Translation Segmentation Network (Trans-Net), which comprises a segmentation network and two boundary discriminators.
1 code implementation • 1 Aug 2021 • Zunlei Feng, Zhonghua Wang, Xinchao Wang, Xiuming Zhang, Lechao Cheng, Jie Lei, Yuexuan Wang, Mingli Song
The diagnosis of MVI needs discovering the vessels that contain hepatocellular carcinoma cells and counting their number in each vessel, which depends heavily on experiences of the doctor, is largely subjective and time-consuming.
1 code implementation • CVPR 2021 • Yongcheng Jing, Yiding Yang, Xinchao Wang, Mingli Song, DaCheng Tao
In this paper, we study a novel knowledge transfer task in the domain of graph neural networks (GNNs).
no code implementations • CVPR 2021 • Jiayan Qiu, Yiding Yang, Xinchao Wang, DaCheng Tao
What scene elements, if any, are indispensable for recognizing a scene?
no code implementations • CVPR 2021 • Jie Song, Haofei Zhang, Xinchao Wang, Mengqi Xue, Ying Chen, Li Sun, DaCheng Tao, Mingli Song
Knowledge distillation pursues a diminutive yet well-behaved student network by harnessing the knowledge learned by a cumbersome teacher model.
no code implementations • CVPR 2021 • Yongcheng Jing, Yiding Yang, Xinchao Wang, Mingli Song, DaCheng Tao
To this end, we propose an Event-based VSR framework (E-VSR), of which the key component is an asynchronous interpolation (EAI) module that reconstructs a high-frequency (HF) video stream with uniform and tiny pixel displacements between neighboring frames from an event stream.
no code implementations • CVPR 2021 • Yiding Yang, Zhou Ren, Haoxiang Li, Chunluan Zhou, Xinchao Wang, Gang Hua
In this paper, we propose a novel online approach to learning the pose dynamics, which are independent of pose detections in current fame, and hence may serve as a robust estimation even in challenging scenarios including occlusion.
2 code implementations • 18 May 2021 • Gongfan Fang, Jie Song, Xinchao Wang, Chengchao Shen, Xingen Wang, Mingli Song
In this paper, we propose Contrastive Model Inversion~(CMI), where the data diversity is explicitly modeled as an optimizable objective, to alleviate the mode collapse issue.
no code implementations • 10 May 2021 • Mengqi Xue, Jie Song, Xinchao Wang, Ying Chen, Xingen Wang, Mingli Song
Knowledge distillation (KD) has recently emerged as an efficacious scheme for learning compact deep neural networks (DNNs).
no code implementations • ICLR 2022 • Dapeng Hu, Shipeng Yan, Qizhengqiu Lu, Lanqing Hong, Hailin Hu, Yifan Zhang, Zhenguo Li, Xinchao Wang, Jiashi Feng
Prior works on self-supervised pre-training focus on the joint training scenario, where massive unlabeled data are assumed to be given as input all at once, and only then is a learner trained.
1 code implementation • CVPR 2021 • Song Guo, Jingya Wang, Xinchao Wang, DaCheng Tao
On the other hand, such reliable embeddings can boost identity-awareness through memory aggregation, hence strengthen attention modules and suppress drifts.
1 code implementation • CVPR 2021 • Chengchao Shen, Youtan Yin, Xinchao Wang, Xubin Li, Jie Song, Mingli Song
Based on the adversarial losses of the generator and discriminator, we categorize GANs into two classes, Symmetric GANs and Asymmetric GANs, and introduce a novel gradient decomposition method to unify the two, allowing us to train both classes in one stage and hence alleviate the training effort.
1 code implementation • 10 Jan 2021 • Yiding Yang, Xinchao Wang, Mingli Song, Junsong Yuan, DaCheng Tao
SPAGAN therefore allows for a more informative and intact exploration of the graph structure and further {a} more effective aggregation of information from distant neighbors into the center node, as compared to node-based GCN methods.
no code implementations • ICCV 2021 • Ying Chen, Feng Mao, Jie Song, Xinchao Wang, Huiqiong Wang, Mingli Song
Neural trees aim at integrating deep neural networks and decision trees so as to bring the best of the two worlds, including representation learning from the former and faster inference from the latter.
no code implementations • ICCV 2021 • Zunlei Feng, Zhonghua Wang, Xinchao Wang, Yining Mao, Thomas Li, Jie Lei, Yuexuan Wang, Mingli Song
The existing two unsupervised methods are prone to failure on degenerated samples.
1 code implementation • ICCV 2021 • Shaoli Huang, Xinchao Wang, DaCheng Tao
Learning mid-level representation for fine-grained recognition is easily dominated by a limited number of highly discriminative patterns, degrading its robustness and generalization capability.
1 code implementation • 10 Dec 2020 • Huihui Liu, Yiding Yang, Xinchao Wang
Catastrophic forgetting refers to the tendency that a neural network "forgets" the previous learned knowledge upon learning new tasks.
2 code implementations • 9 Dec 2020 • Shaoli Huang, Xinchao Wang, DaCheng Tao
As the main discriminative information of a fine-grained image usually resides in subtle regions, methods along this line are prone to heavy label noise in fine-grained recognition.
Ranked #30 on
Fine-Grained Image Classification
on CUB-200-2011
1 code implementation • 9 Dec 2020 • Chengchao Shen, Xinchao Wang, Youtan Yin, Jie Song, Sihui Luo, Mingli Song
In this paper, we investigate the practical few-shot knowledge distillation scenario, where we assume only a few samples without human annotations are available for each category.
no code implementations • NeurIPS 2020 • Zunlei Feng, Yongming He, Xinchao Wang, Xin Gao, Jie Lei, Cheng Jin, Mingli Song
In this paper, we introduce the One-sample Guided Object Representation Disassembling (One-GORD) method, which only requires one annotated sample for each object category to learn disassembled object representation from unannotated images.
no code implementations • ECCV 2020 • Yiding Yang, Jiayan Qiu, Mingli Song, DaCheng Tao, Xinchao Wang
Prior gradient-based attribution-map methods rely on handcrafted propagation rules for the non-linear/activation layers during the backward pass, so as to produce gradients of the input and then the attribution map.
1 code implementation • NeurIPS 2020 • Yiding Yang, Zunlei Feng, Mingli Song, Xinchao Wang
In this paper, we introduce a novel graph convolutional network (GCN), termed as factorizable graph convolutional network(FactorGCN), that explicitly disentangles such intertwined relations encoded in a graph.
Ranked #3 on
Node Classification
on PATTERN 100k
no code implementations • 18 Jul 2020 • Weihong Ren, Xinchao Wang, Jiandong Tian, Yandong Tang, Antoni B. Chan
State-of-the-art multi-object tracking~(MOT) methods follow the tracking-by-detection paradigm, where object trajectories are obtained by associating per-frame outputs of object detectors.
no code implementations • 10 Jul 2020 • Gongfan Fang, Xinchao Wang, Haofei Zhang, Jie Song, Mingli Song
This network is referred to as the {\emph{Template Network}} because its filters will be used as templates to reconstruct images from the impression.
no code implementations • 3 Apr 2020 • Zunlei Feng, Xinchao Wang, Yongming He, Yike Yuan, Xin Gao, Mingli Song
In this paper, we study a new representation-learning task, which we termed as disassembling object representations.
no code implementations • CVPR 2020 • Tong Zhou, Changxing Ding, Shaowen Lin, Xinchao Wang, DaCheng Tao
While recent works adopted the attention mechanism to learn the contextual relations among elements of the face, they have largely overlooked the disastrous impacts of inaccurate attention scores; in addition, they fail to pay sufficient attention to key facial components, the completion results of which largely determine the authenticity of a face image.
1 code implementation • CVPR 2020 • Yiding Yang, Jiayan Qiu, Mingli Song, DaCheng Tao, Xinchao Wang
To enable the knowledge transfer from the teacher GCN to the student, we propose a local structure preserving module that explicitly accounts for the topological semantics of the teacher.
no code implementations • CVPR 2020 • Jingwen Ye, Yixin Ji, Xinchao Wang, Xin Gao, Mingli Song
Then a dual generator is trained by taking the output from the former generator as input.
1 code implementation • CVPR 2020 • Jie Song, Yixin Chen, Jingwen Ye, Xinchao Wang, Chengchao Shen, Feng Mao, Mingli Song
In this paper, we propose the DEeP Attribution gRAph (DEPARA) to investigate the transferability of knowledge learned from PR-DNNs.
2 code implementations • 23 Dec 2019 • Gongfan Fang, Jie Song, Chengchao Shen, Xinchao Wang, Da Chen, Mingli Song
Knowledge Distillation (KD) has made remarkable progress in the last few years and become a popular paradigm for model compression and knowledge transfer.
no code implementations • 26 Nov 2019 • Ya Zhao, Rui Xu, Xinchao Wang, Peng Hou, Haihong Tang, Mingli Song
In this paper, we propose a new method, termed as Lip by Speech (LIBS), of which the goal is to strengthen lip reading by learning from speech recognizers.
Ranked #2 on
Lipreading
on CMLR
no code implementations • 16 Nov 2019 • Yongcheng Jing, Xiao Liu, Yukang Ding, Xinchao Wang, Errui Ding, Mingli Song, Shilei Wen
Prior normalization methods rely on affine transformations to produce arbitrary image style transfers, of which the parameters are computed in a pre-defined way.
1 code implementation • NeurIPS 2019 • Jie Song, Yixin Chen, Xinchao Wang, Chengchao Shen, Mingli Song
Exploring the transferability between heterogeneous tasks sheds light on their intrinsic interconnections, and consequently enables knowledge transfer from one task to another so as to reduce the training effort of the latter.
1 code implementation • ICCV 2019 • Chengchao Shen, Mengqi Xue, Xinchao Wang, Jie Song, Li Sun, Mingli Song
To this end, we introduce a dual-step strategy that first extracts the task-specific knowledge from the heterogeneous teachers sharing the same sub-task, and then amalgamates the extracted knowledge to build the student network.
2 code implementations • 24 Jun 2019 • Sihui Luo, Xinchao Wang, Gongfan Fang, Yao Hu, Dapeng Tao, Mingli Song
An increasing number of well-trained deep networks have been released online by researchers and developers, enabling the community to reuse them in a plug-and-play way without accessing the training annotations.
1 code implementation • 5 Jun 2019 • Chenhong Zhou, Changxing Ding, Xinchao Wang, Zhentai Lu, DaCheng Tao
The model cascade (MC) strategy significantly alleviates the class imbalance issue via running a set of individual deep models for coarse-to-fine segmentation.
Ranked #1 on
Brain Tumor Segmentation
on BRATS-2015
1 code implementation • 28 May 2019 • Jingwen Ye, Xinchao Wang, Yixin Ji, Kairi Ou, Mingli Song
Many well-trained Convolutional Neural Network(CNN) models have now been released online by developers for the sake of effortless reproducing.
no code implementations • 20 May 2019 • Jue Wang, Shaoli Huang, Xinchao Wang, DaCheng Tao
We model parts with higher DOFs like the elbows, as dependent components of the corresponding parts with lower DOFs like the torso, of which the 3D locations can be more reliably estimated.
1 code implementation • CVPR 2019 • Jingwen Ye, Yixin Ji, Xinchao Wang, Kairi Ou, Dapeng Tao, Mingli Song
In this paper, we investigate a novel deep-model reusing task.
no code implementations • 12 Apr 2019 • Yu Zhang, Xinchao Wang, Xiaojun Bi, DaCheng Tao
In LDTNet, the haze-free image and the transmission map are produced simultaneously.
1 code implementation • 7 Nov 2018 • Chengchao Shen, Xinchao Wang, Jie Song, Li Sun, Mingli Song
We propose in this paper to study a new model-reusing task, which we term as \emph{knowledge amalgamation}.
10 code implementations • 27 Aug 2018 • Jiahui Yu, Yuchen Fan, Jianchao Yang, Ning Xu, Zhaowen Wang, Xinchao Wang, Thomas Huang
Keras-based implementation of WDSR, EDSR and SRGAN for single image super-resolution
Ranked #4 on
Multi-Frame Super-Resolution
on PROBA-V
no code implementations • CVPR 2018 • Fangfang Wang, Liming Zhao, Xi Li, Xinchao Wang, DaCheng Tao
Localizing text in the wild is challenging in the situations of complicated geometric layout of the targets like random orientation and large aspect ratio.
1 code implementation • NeurIPS 2018 • Zunlei Feng, Xinchao Wang, Chenglong Ke, An-Xiang Zeng, DaCheng Tao, Mingli Song
To achieve disentangling using the labeled pairs, we follow a "encoding-swap-decoding" process, where we first swap the parts of their encodings corresponding to the shared attribute and then decode the obtained hybrid codes to reconstruct the original input pairs.
no code implementations • 22 Apr 2018 • Fusheng Hao, Jun Cheng, Lei Wang, Xinchao Wang, Jianzhong Cao, Xiping Hu, Dapeng Tao
Discriminative features are obtained by constraining the deep CNNs to map training samples to the corresponding anchors as close as possible.
1 code implementation • 14 Apr 2018 • Yang Fu, Yunchao Wei, Yuqian Zhou, Honghui Shi, Gao Huang, Xinchao Wang, Zhiqiang Yao, Thomas Huang
Despite the remarkable recent progress, person re-identification (Re-ID) approaches are still suffering from the failure cases where the discriminative body parts are missing.
Ranked #53 on
Person Re-Identification
on DukeMTMC-reID
no code implementations • 13 Apr 2018 • Xiaoqing Yin, Xiyang Dai, Xinchao Wang, Maojun Zhang, DaCheng Tao, Larry Davis
In this paper, we propose the first dedicated end-to-end deep learning approach for motion boundary detection, which we term as MoBoNet.
no code implementations • ECCV 2018 • Xiaoqing Yin, Xinchao Wang, Jun Yu, Maojun Zhang, Pascal Fua, DaCheng Tao
Images captured by fisheye lenses violate the pinhole camera assumption and suffer from distortions.
no code implementations • 14 Dec 2017 • Bin Fan, Qingqun Kong, Xinchao Wang, Zhiheng Wang, Shiming Xiang, Chunhong Pan, Pascal Fua
To obtain a comprehensive evaluation, we choose to include both float type features and binary ones.
2 code implementations • 4 Dec 2017 • Zhiqiang Shen, Honghui Shi, Jiahui Yu, Hai Phan, Rogerio Feris, Liangliang Cao, Ding Liu, Xinchao Wang, Thomas Huang, Marios Savvides
In this paper, we present a simple and parameter-efficient drop-in module for one-stage object detectors like SSD when learning from scratch (i. e., without pre-trained models).
no code implementations • ICCV 2017 • Andrii Maksai, Xinchao Wang, Francois Fleuret, Pascal Fua
Many state-of-the-art approaches to multi-object tracking rely on detecting them in each frame independently, grouping detections into short but reliable trajectory segments, and then further grouping them into full trajectories.
no code implementations • CVPR 2017 • Xiyu Yu, Tongliang Liu, Xinchao Wang, DaCheng Tao
Deep compression refers to removing the redundancy of parameters and feature maps for deep learning models.
1 code implementation • 2 Dec 2016 • Andrii Maksai, Xinchao Wang, Francois Fleuret, Pascal Fua
Many state-of-the-art approaches to people tracking rely on detecting them in each frame independently, grouping detections into short but reliable trajectory segments, and then further grouping them into full trajectories.
no code implementations • 14 Feb 2016 • Bin Fan, Qingqun Kong, Wei Sui, Zhiheng Wang, Xinchao Wang, Shiming Xiang, Chunhong Pan, Pascal Fua
Binary features have been incrementally popular in the past few years due to their low memory footprints and the efficient computation of Hamming distance between binary descriptors.
no code implementations • CVPR 2016 • Andrii Maksai, Xinchao Wang, Pascal Fua
Tracking the ball is critical for video-based analysis of team sports.
no code implementations • 30 Apr 2015 • Bugra Tekin, Xiaolu Sun, Xinchao Wang, Vincent Lepetit, Pascal Fua
We propose an efficient approach to exploiting motion information from consecutive frames of a video sequence to recover the 3D pose of people.
no code implementations • arXiv:1504.08200 Search... Help | Advanced Search 2015 • Bugra Tekin, Xiaolu Sun, Xinchao Wang, Vincent Lepetit, Pascal Fua
We propose an efficient approach to exploiting motion information from consecutive frames of a video sequence to recover the 3D pose of people.
Ranked #268 on
3D Human Pose Estimation
on Human3.6M
no code implementations • 22 Jan 2015 • Engin Türetken, Xinchao Wang, Carlos Becker, Carsten Haubold, Pascal Fua
We propose a novel approach to automatically tracking cell populations in time-lapse images.
no code implementations • 6 Sep 2014 • Vasileios Belagiannis, Xinchao Wang, Bernt Schiele, Pascal Fua, Slobodan Ilic, Nassir Navab
To address these challenges, we propose a temporally consistent 3D Pictorial Structures model (3DPS) for multiple human pose estimation from multiple camera views.
Ranked #16 on
3D Multi-Person Pose Estimation
on Campus