no code implementations • ECCV 2020 • Kunyuan Du, Ya zhang, Haibing Guan, Qi Tian, Shenggan Cheng, James Lin
Compared with low-bit models trained directly, the proposed framework brings 0. 5% to 3. 4% accuracy gains to three different quantization schemes.
no code implementations • 12 Jan 2023 • Ziyi Li, Qinye Zhou, Xiaoyun Zhang, Ya zhang, Yanfeng Wang, Weidi Xie
The goal of this paper is to augment a pre-trained text-to-image diffusion model with the ability of open-vocabulary objects grounding, i. e., simultaneously generating images and segmentation masks for the corresponding visual entities described in the text prompt.
no code implementations • 9 Jan 2023 • Chaoyi Wu, Feng Chang, Xiao Su, Zhihan Wu, Yanfeng Wang, Ling Zhu, Ya zhang
The branch targets to solve a closely related task on the LN station level, i. e., classifying whether an LN station contains metastatic LN or not, so as to learn representations for LN stations.
no code implementations • 5 Jan 2023 • Chaoyi Wu, Xiaoman Zhang, Ya zhang, Yanfeng Wang, Weidi Xie
In this paper, we consider the problem of enhancing self-supervised visual-language pre-training (VLP) with medical-specific knowledge, by exploiting the paired image-text reports from the radiological daily practice.
no code implementations • 29 Dec 2022 • Shengchao Hu, Li Shen, Ya zhang, Yixin Chen, DaCheng Tao
Transformer, originally devised for natural language processing, has also attested significant success in computer vision.
no code implementations • 19 Dec 2022 • Chen Ju, Kunhao Zheng, Jinxiang Liu, Peisen Zhao, Ya zhang, Jianlong Chang, Yanfeng Wang, Qi Tian
And as a result, the dual-branch complementarity is effectively fused to promote a strong alliance.
Weakly-supervised Temporal Action Localization
Weakly Supervised Temporal Action Localization
1 code implementation • 14 Dec 2022 • Ziqing Fan, Yanfeng Wang, Jiangchao Yao, Lingjuan Lyu, Ya zhang, Qi Tian
However, in addition to previous explorations for improvement in federated averaging, our analysis shows that another critical bottleneck is the poorer optima of client models in more heterogeneous conditions.
no code implementations • 27 Oct 2022 • Chaofan Ma, Yuhuan Yang, Yanfeng Wang, Ya zhang, Weidi Xie
When trained at a sufficient scale, self-supervised learning has exhibited a notable ability to solve a wide range of visual or language understanding tasks.
no code implementations • 7 Oct 2022 • Qinye Zhou, Ziyi Li, Weidi Xie, Xiaoyun Zhang, Ya zhang, Yanfeng Wang
Existing models on super-resolution often specialized for one scale, fundamentally limiting their use in practical scenarios.
no code implementations • 20 Aug 2022 • Wentao Liu, Chaofan Ma, Yuhuan Yang, Weidi Xie, Ya zhang
The goal of this paper is to interactively refine the automatic segmentation on challenging structures that fall behind human performance, either due to the scarcity of available annotations or the difficulty nature of the problem itself, for example, on segmenting cancer or small organs.
1 code implementation • 8 Aug 2022 • Yue Hu, Siheng Chen, Xu Chen, Ya zhang, Xiao Gu
Visual relationship detection aims to detect the interactions between objects in an image; however, this task suffers from combinatorial explosion due to the variety of objects and interactions.
1 code implementation • 31 Jul 2022 • Maosen Li, Siheng Chen, Zijing Zhang, Lingxi Xie, Qi Tian, Ya zhang
To address the first issue, we propose adaptive graph scattering, which leverages multiple trainable band-pass graph filters to decompose pose features into richer graph spectrum bands.
1 code implementation • 15 Jul 2022 • Chaoqin Huang, Haoyan Guan, Aofan Jiang, Ya zhang, Michael Spratling, Yan-Feng Wang
Inspired by how humans detect anomalies, i. e., comparing an image in question to normal images, we here leverage registration, an image alignment task that is inherently generalizable across categories, as the proxy task, to train a category-agnostic anomaly detection model.
Ranked #47 on
Anomaly Detection
on MVTec AD
no code implementations • 11 Jul 2022 • Bohan Tang, Yiqi Zhong, Chenxin Xu, Wei-Tao Wu, Ulrich Neumann, Yanfeng Wang, Ya zhang, Siheng Chen
Further, we apply the proposed framework to current SOTA multi-agent multi-modal forecasting systems as a plugin module, which enables the SOTA systems to 1) estimate the uncertainty in the multi-agent multi-modal trajectory forecasting task; 2) rank the multiple predictions and select the optimal one based on the estimated uncertainty.
1 code implementation • 27 Jun 2022 • Chenxin Xu, Yuxi Wei, Bohan Tang, Sheng Yin, Ya zhang, Siheng Chen
Demystifying the interactions among multiple agents from their past trajectories is fundamental to precise and interpretable trajectory prediction.
no code implementations • 26 Jun 2022 • Jinxiang Liu, Chen Ju, Weidi Xie, Ya zhang
We present a simple yet effective self-supervised framework for audio-visual representation learning, to localize the sound source in videos.
1 code implementation • 14 Jun 2022 • Ziheng Zhao, Tianjiao Zhang, Weidi Xie, Yanfeng Wang, Ya zhang
This paper considers the problem of undersampled MRI reconstruction.
1 code implementation • 25 May 2022 • Zhihan Zhou, Jiangchao Yao, Yanfeng Wang, Bo Han, Ya zhang
Different from previous works, we explore this direction from an alternative perspective, i. e., the data perspective, and propose a novel Boosted Contrastive Learning (BCL) method.
no code implementations • 13 May 2022 • Chaoqin Huang, Qinwei Xu, Yanfeng Wang, Yu Wang, Ya zhang
To extend the reconstruction-based anomaly detection architecture to the localized anomalies, we propose a self-supervised learning approach through random masking and then restoring, named Self-Supervised Masking (SSM) for unsupervised anomaly detection and localization.
1 code implementation • CVPR 2022 • Chenxin Xu, Maosen Li, Zhenyang Ni, Ya zhang, Siheng Chen
From the aspect of interaction capturing, we propose a trainable multiscale hypergraph to capture both pair-wise and group-wise interactions at multiple group sizes.
no code implementations • CVPR 2022 • Yixuan Huang, Xiaoyun Zhang, Yu Fu, Siheng Chen, Ya zhang, Yan-Feng Wang, Dazhi He
Those methods conduct the super-resolution task of the input low-resolution(LR) image and the texture transfer task from the reference image together in one module, easily introducing the interference between LR and reference features.
no code implementations • CVPR 2022 • Baisong Guo, Xiaoyun Zhang, HaoNing Wu, Yu Wang, Ya zhang, Yan-Feng Wang
Previous super-resolution (SR) approaches often formulate SR as a regression problem and pixel wise restoration, which leads to a blurry and unreal SR output.
1 code implementation • 8 Dec 2021 • Chen Ju, Tengda Han, Kunhao Zheng, Ya zhang, Weidi Xie
Image-based visual-language (I-VL) pre-training has shown great success for learning joint visual-textual representations from large-scale web data, revealing remarkable ability for zero-shot generalisation.
Ranked #2 on
Zero-Shot Action Detection
on ActivityNet-1.3
no code implementations • NeurIPS 2021 • Bohan Tang, Yiqi Zhong, Ulrich Neumann, Gang Wang, Ya zhang, Siheng Chen
2) The results of trajectory forecasting benchmarks demonstrate that the CU-based framework steadily helps SOTA systems improve their performances.
no code implementations • 23 Oct 2021 • Zida Cheng, Siheng Chen, Ya zhang
Spatio-temporal graph signal analysis has a significant impact on a wide range of applications, including hand/body pose action recognition.
no code implementations • 27 Sep 2021 • Yujie Pan, Jiangchao Yao, Bo Han, Kunyang Jia, Ya zhang, Hongxia Yang
Click-through rate (CTR) prediction becomes indispensable in ubiquitous web recommendation applications.
no code implementations • 24 Sep 2021 • Jinxiang Liu, Yangheng Zhao, Siheng Chen, Ya zhang
To leverage the human body shape prior, LPNet exploits the topological information of the body mesh to learn an expressive visual representation for the target person in the 3D mesh space.
no code implementations • 7 Sep 2021 • Xiaoman Zhang, Weidi Xie, Chaoqin Huang, Yanfeng Wang, Ya zhang, Xin Chen, Qi Tian
In this paper, we target self-supervised representation learning for zero-shot tumor segmentation.
no code implementations • 25 Aug 2021 • Maosen Li, Siheng Chen, Yangheng Zhao, Ya zhang, Yanfeng Wang, Qi Tian
The core of MST-GNN is a multiscale spatio-temporal graph that explicitly models the relations in motions at various spatial and temporal scales.
no code implementations • ICCV 2021 • Tianyue Cao, Lianyu Du, Xiaoyun Zhang, Siheng Chen, Ya zhang, Yan-Feng Wang
To handle overlapping category transfer, we propose a double-supervision mean teacher to gather common category information and bridge the domain gap between two datasets.
no code implementations • 11 Aug 2021 • Hao Wu, Jiangchao Yao, Ya zhang, Yanfeng Wang
Learning with noisy labels has gained the enormous interest in the robust deep learning area.
no code implementations • 5 Aug 2021 • Shixiang Feng, YuHang Zhou, Xiaoman Zhang, Ya zhang, Yanfeng Wang
A novel Multi-teacher Single-student Knowledge Distillation (MS-KD) framework is proposed, where the teacher models are pre-trained single-organ segmentation networks, and the student model is a multi-organ segmentation network.
no code implementations • 16 Jul 2021 • Zida Cheng, Siheng Chen, Ya zhang
Experiments are conducted on FPHA and HO-3D datasets.
no code implementations • 2 Jul 2021 • Maosen Li, Siheng Chen, Yanning Shen, Genjia Liu, Ivor W. Tsang, Ya zhang
This paper considers predicting future statuses of multiple agents in an online fashion by exploiting dynamic interactions in the system.
no code implementations • 17 Jun 2021 • Minhao Hu, Matthis Maillard, Ya zhang, Tommaso Ciceri, Giammarco La Barbera, Isabelle Bloch, Pietro Gori
In this paper, we propose KD-Net, a framework to transfer knowledge from a trained multi-modal network (teacher) to a mono-modal one (student).
1 code implementation • CVPR 2021 • Qinwei Xu, Ruipeng Zhang, Ya zhang, Yanfeng Wang, Qi Tian
Modern deep neural networks suffer from performance degradation when evaluated on testing data under different distributions from training data.
no code implementations • 8 May 2021 • Huangjie Zheng, Xu Chen, Jiangchao Yao, Hongxia Yang, Chunyuan Li, Ya zhang, Hao Zhang, Ivor Tsang, Jingren Zhou, Mingyuan Zhou
We realize this strategy with contrastive attraction and contrastive repulsion (CACR), which makes the query not only exert a greater force to attract more distant positive samples but also do so to repel closer negative samples.
no code implementations • 15 Apr 2021 • Zhenfeng Shao, Yong Li, Xiao Huang, Bowen Cai, Lin Ding, Wenkang Pan, Ya zhang
Ecosystem valuation is a method of assigning a monetary value to an ecosystem with its goods and services, often referred to as ecosystem service value (ESV).
no code implementations • 6 Apr 2021 • Chen Ju, Peisen Zhao, Siheng Chen, Ya zhang, Xiaoyun Zhang, Qi Tian
To solve this issue, we introduce an adaptive mutual supervision framework (AMS) with two branches, where the base branch adopts CAS to localize the most discriminative action regions, while the supplementary branch localizes the less discriminative action regions through a novel adaptive sampler.
Ranked #5 on
Weakly Supervised Action Localization
on THUMOS14
Weakly Supervised Action Localization
Weakly-supervised Temporal Action Localization
+1
no code implementations • 31 Mar 2021 • Hao Wu, Jiangchao Yao, Jiajie Wang, Yinru Chen, Ya zhang, Yanfeng Wang
Deep neural networks (DNNs) have the capacity to fit extremely noisy labels nonetheless they tend to learn data with clean labels first and then memorize those with noisy labels.
no code implementations • 23 Mar 2021 • Mingming Lu, Ya zhang
Graph Neural Networks (GNNs) have attracted increasing attention due to its successful applications on various graph-structure data.
no code implementations • 9 Mar 2021 • Jieneng Chen, Ke Yan, Yu-Dong Zhang, YouBao Tang, Xun Xu, Shuwen Sun, Qiuping Liu, Lingyun Huang, Jing Xiao, Alan L. Yuille, Ya zhang, Le Lu
(2) The sampled deep vertex features with positional embedding are mapped into a sequential space and decoded by a multilayer perceptron (MLP) for semantic classification.
no code implementations • 9 Mar 2021 • YuHang Zhou, Xiaoman Zhang, Shixiang Feng, Ya zhang, Yanfeng
Specifically, given a pretrained $K$ organ segmentation model and a new single-organ dataset, we train a unified $K+1$ organ segmentation model without accessing any data belonging to the previous training stages.
no code implementations • ICCV 2021 • Chen Ju, Peisen Zhao, Siheng Chen, Ya zhang, Yanfeng Wang, Qi Tian
Single-frame temporal action localization (STAL) aims to localize actions in untrimmed videos with only one timestamp annotation for each action instance.
1 code implementation • 17 Dec 2020 • Chenxin Xu, Siheng Chen, Maosen Li, Ya zhang
To handle the decomposition ambiguity in the teacher network, we propose a cycle-consistent architecture promoting a 3D rotation-invariant property to train the teacher network.
no code implementations • 15 Dec 2020 • Chen Ju, Peisen Zhao, Ya zhang, Yanfeng Wang, Qi Tian
Point-Level temporal action localization (PTAL) aims to localize actions in untrimmed videos with only one timestamp annotation for each action instance.
Ranked #2 on
Weakly Supervised Action Localization
on BEOID
no code implementations • 9 Dec 2020 • Fei Ye, Huangjie Zheng, Chaoqin Huang, Ya zhang
Based on this object function we introduce a novel information theoretic framework for unsupervised image anomaly detection.
Ranked #8 on
Anomaly Detection
on One-class CIFAR-100
no code implementations • 9 Dec 2020 • Chaoqin Huang, Fei Ye, Peisen Zhao, Ya zhang, Yan-Feng Wang, Qi Tian
This paper explores semi-supervised anomaly detection, a more practical setting for anomaly detection where a small additional set of labeled samples are provided.
Ranked #24 on
Anomaly Detection
on One-class CIFAR-10
(using extra training data)
no code implementations • 18 Nov 2020 • Peisen Zhao, Lingxi Xie, Ya zhang, Yanfeng Wang, Qi Tian
Knowledge distillation is employed to transfer the privileged information from the offline teacher to the online student.
Ranked #5 on
Online Action Detection
on TVSeries
3 code implementations • 3 Nov 2020 • Xu Chen, Siheng Chen, Jiangchao Yao, Huangjie Zheng, Ya zhang, Ivor W Tsang
Thereby, designing a new GNN for these graphs is a burning issue to the graph learning community.
no code implementations • 3 Nov 2020 • Siheng Chen, Maosen Li, Ya zhang
Compared to previous analytical sampling and recovery, the proposed methods are able to flexibly learn a variety of graph signal models from data by leveraging the learning ability of neural networks; compared to previous neural-network-based sampling and recovery, the proposed methods are designed through exploiting specific graph properties and provide interpretability.
no code implementations • 13 Oct 2020 • Shixiang Feng, Beibei Liu, Ya zhang, Xiaoyun Zhang, Yuehua Li
In this paper, we explore to model VCFs diagnosis as a three-class classification problem, i. e. normal vertebrae, benign VCFs, and malignant VCFs.
no code implementations • 13 Oct 2020 • Xiaoman Zhang, Shixiang Feng, YuHang Zhou, Ya zhang, Yanfeng Wang
We demonstrate the effectiveness of our methods on two downstream tasks: i) Brain tumor segmentation, ii) Pancreas tumor segmentation.
2 code implementations • NeurIPS 2020 • Maosen Li, Siheng Chen, Ya zhang, Ivor W. Tsang
Based on trainable hierarchical representations of a graph, GXN enables the interchange of intermediate features across scales to promote information flow.
no code implementations • 17 Sep 2020 • Ya Zhang, Mingming Lu, Haifeng Li
Traffic forecasting is an important prerequisite for the application of intelligent transportation systems in urban traffic networks.
1 code implementation • 15 Sep 2020 • Xu Chen, Ya zhang, Ivor Tsang, Yuangang Pan, Jingchao Su
In this paper, we attempt to learn both features of user preferences in a more principled way.
1 code implementation • 28 Aug 2020 • Xu Chen, Jiangchao Yao, Maosen Li, Ya zhang, Yan-Feng Wang
Comprehensive results on both link sign prediction and node recommendation task demonstrate the effectiveness of DVE.
no code implementations • 26 Aug 2020 • Xu Chen, Ya zhang, Ivor Tsang, Yuangang Pan
Graph neural networks (GNN), as a popular methodology for node representation learning on graphs, currently mainly focus on preserving the smoothness and identifiability of node representations.
no code implementations • 16 Jul 2020 • Chenyang Li, Xu Chen, Ya zhang, Siheng Chen, Dan Lv, Yan-Feng Wang
Most existing methods focus on preserving the first-order proximity between entities in the KG.
no code implementations • 16 Jul 2020 • Jingchao Su, Xu Chen, Ya zhang, Siheng Chen, Dan Lv, Chenyang Li
The two-level alignment acts as two different constraints on different relations of the shared entities and facilitates better knowledge transfer for relational learning on multiple bipartite graphs.
no code implementations • 13 Jul 2020 • Peisen Zhao, Lingxi Xie, Ya zhang, Qi Tian
The U2S framework is composed of three subnetworks: a universal network, a category-specific network, and a mask network.
no code implementations • 11 Apr 2020 • Kunyuan Du, Ya zhang, Haibing Guan
This paper proposes Quantizable DNNs, a special type of DNNs that can flexibly quantize its bit-width (denoted as `bit modes' thereafter) during execution without further re-training.
1 code implementation • 17 Mar 2020 • Maosen Li, Siheng Chen, Yangheng Zhao, Ya zhang, Yan-Feng Wang, Qi Tian
The core idea of DMGNN is to use a multiscale graph to comprehensively model the internal relations of a human body for motion feature learning.
1 code implementation • CVPR 2020 • Yue Hu, Siheng Chen, Ya zhang, Xiao Gu
Motion prediction is essential and challenging for autonomous vehicles and social robots.
1 code implementation • ECCV 2020 • Peisen Zhao, Lingxi Xie, Chen Ju, Ya zhang, Yan-Feng Wang, Qi Tian
To alleviate this problem, we introduce two regularization terms to mutually regularize the learning procedure: the Intra-phase Consistency (IntraC) regularization is proposed to make the predictions verified inside each phase; and the Inter-phase Consistency (InterC) regularization is proposed to keep consistency between these phases.
1 code implementation • 25 Nov 2019 • Chaoqin Huang, Fei Ye, Jinkun Cao, Maosen Li, Ya zhang, Cewu Lu
We here propose to break this equivalence by erasing selected attributes from the original data and reformulate it as a restoration task, where the normal and the anomalous data are expected to be distinguishable based on restoration errors.
Ranked #20 on
Anomaly Detection
on One-class CIFAR-10
no code implementations • CVPR 2020 • Xuan Liao, Wenhao Li, Qisen Xu, Xiangfeng Wang, Bo Jin, Xiaoyun Zhang, Ya zhang, Yan-Feng Wang
We here propose to model the dynamic process of iterative interactive image segmentation as a Markov decision process (MDP) and solve it with reinforcement learning (RL).
no code implementations • 17 Oct 2019 • Xu Chen, Kenan Cui, Ya zhang, Yan-Feng Wang
Recently, recommendation according to sequential user behaviors has shown promising results in many application scenarios.
no code implementations • 5 Oct 2019 • Maosen Li, Siheng Chen, Xu Chen, Ya zhang, Yan-Feng Wang, Qi Tian
For the backbone, we propose multi-branch multi-scale graph convolution networks to extract spatial and temporal features.
Ranked #28 on
Skeleton Based Action Recognition
on NTU RGB+D
no code implementations • 19 Sep 2019 • Zhuoxun He, Lingxi Xie, Xin Chen, Ya zhang, Yan-Feng Wang, Qi Tian
Data augmentation has been widely applied as an effective methodology to improve generalization in particular when training deep neural networks.
3 code implementations • 23 Jul 2019 • Xu Chen, Siheng Chen, Huangjie Zheng, Jiangchao Yao, Kenan Cui, Ya zhang, Ivor W. Tsang
NANG learns a unifying latent representation which is shared by both node attributes and graph structures and can be translated to different modalities.
no code implementations • 26 Jun 2019 • Yifeng Li, Lingxi Xie, Ya zhang, Rui Zhang, Yanfeng Wang, Qi Tian
Generating and eliminating adversarial examples has been an intriguing topic in the field of deep learning.
no code implementations • 30 Apr 2019 • Chuan Wen, Jie Chang, Ya zhang, Siheng Chen, Yan-Feng Wang, Mei Han, Qi Tian
Automatic character generation is an appealing solution for new typeface design, especially for Chinese typefaces including over 3700 most commonly-used characters.
1 code implementation • CVPR 2019 • Maosen Li, Siheng Chen, Xu Chen, Ya zhang, Yan-Feng Wang, Qi Tian
We validate AS-GCN in action recognition using two skeleton data sets, NTU-RGB+D and Kinetics.
1 code implementation • 6 Mar 2019 • Jiangchao Yao, Ya zhang, Ivor W. Tsang, Jun Sun
We further generalize LCCN for open-set noisy labels and the semi-supervised setting.
Ranked #33 on
Image Classification
on Clothing1M
(using extra training data)
no code implementations • ICCV 2019 • Yuefu Zhou, Ya zhang, Yan-Feng Wang, Qi Tian
A new dropout-based measurement of redundancy, which facilitate the computation of posterior assuming inter-layer dependency, is introduced.
no code implementations • 30 Nov 2018 • Yexun Zhang, Ya zhang, Yan-Feng Wang, Qi Tian
Unsupervised domain adaption aims to learn a powerful classifier for the target domain given a labeled source data set and an unlabeled target data set.
no code implementations • 28 Nov 2018 • Huangjie Zheng, Lingxi Xie, Tianwei Ni, Ya zhang, Yan-Feng Wang, Qi Tian, Elliot K. Fishman, Alan L. Yuille
However, in medical image analysis, fusing prediction from two phases is often difficult, because (i) there is a domain gap between two phases, and (ii) the semantic labels are not pixel-wise corresponded even for images scanned from the same patient.
no code implementations • 22 Sep 2018 • Kenan Cui, Xu Chen, Jiangchao Yao, Ya zhang
Conventional CF-based methods use the user-item interaction data as the sole information source to recommend items to users.
1 code implementation • 11 Aug 2018 • Kan Ren, Yuchen Fang, Wei-Nan Zhang, Shuhao Liu, Jiajun Li, Ya zhang, Yong Yu, Jun Wang
To achieve this, we utilize sequence-to-sequence prediction for user clicks, and combine both post-view and post-click attribution patterns together for the final conversion estimation.
no code implementations • 10 Jul 2018 • Huangjie Zheng, Jiangchao Yao, Ya zhang, Ivor W. Tsang, Jia Wang
In information theory, Fisher information and Shannon information (entropy) are respectively used to quantify the uncertainty associated with the distribution modeling and the uncertainty in specifying the outcome of given variables.
1 code implementation • 13 Jun 2018 • Yexun Zhang, Ya zhang, Wenbin Cai
The encoders are expected to capture the underlying features for different styles and contents which is generalizable to new styles and contents.
no code implementations • 29 May 2018 • Yu Li, Ya zhang
Web page saliency prediction is a challenge problem in image transformation and computer vision.
2 code implementations • NeurIPS 2018 • Bo Han, Jiangchao Yao, Gang Niu, Mingyuan Zhou, Ivor Tsang, Ya zhang, Masashi Sugiyama
It is important to learn various types of classifiers given training data with noisy labels.
Ranked #39 on
Image Classification
on Clothing1M
(using extra training data)
no code implementations • 27 Apr 2018 • Yujun Gu, Jie Chang, Ya zhang, Yan-Feng Wang
Understanding human visual attention is important for multimedia applications.
no code implementations • 12 Apr 2018 • Jiangchao Yao, Ivor Tsang, Ya zhang
Learning in the latent variable model is challenging in the presence of the complex data structure or the intractable latent variable.
no code implementations • ECCV 2018 • Yan Wang, Lingxi Xie, Siyuan Qiao, Ya zhang, Wenjun Zhang, Alan L. Yuille
Convolution is spatially-symmetric, i. e., the visual features are independent of its position in the image, which limits its ability to utilize contextual cues for visual recognition.
no code implementations • 19 Feb 2018 • Huangjie Zheng, Jiangchao Yao, Ya zhang, Ivor W. Tsang
While enormous progress has been made to Variational Autoencoder (VAE) in recent years, similar to other deep networks, VAE with deep networks suffers from the problem of degeneration, which seriously weakens the correlation between the input and the corresponding latent codes, deviating from the goal of the representation learning.
no code implementations • 10 Feb 2018 • Jiajie Wang, Jiangchao Yao, Ya zhang, Rui Zhang
For object detection, taking WSDDN-like architecture as weakly supervised detector sub-network and Faster-RCNN-like architecture as strongly supervised detector sub-network, we propose an end-to-end Weakly Supervised Collaborative Detection Network.
1 code implementation • CVPR 2018 • Yexun Zhang, Ya zhang, Wenbin Cai, Jie Chang
We here attempt to separate the representations for styles and contents, and propose a generalized style transfer network consisting of style encoder, content encoder, mixer and decoder.
no code implementations • 17 Nov 2017 • Jie Chang, Yujun Gu, Ya zhang
Inspired by the recent advancement in Generative Adversarial Networks (GANs), we propose a Hierarchical Adversarial Network (HAN) for typeface transformation.
no code implementations • 2 Nov 2017 • Jiangchao Yao, Jiajie Wang, Ivor Tsang, Ya zhang, Jun Sun, Chengqi Zhang, Rui Zhang
However, the label noise among the datasets severely degenerates the \mbox{performance of deep} learning approaches.
no code implementations • 1 Nov 2017 • Zhuoxiang Chen, Zhe Xu, Ya zhang, Xiao Gu
We model this problem as a new type of image retrieval task in which the target image resides only in the user's mind (called "mental image retrieval" hereafter).
no code implementations • 31 Oct 2017 • Zhonghao Wang, Yujun Gu, Ya zhang, Jun Zhou, Xiao Gu
The VAM is further connected to a global network to form an end-to-end network structure through Impdrop connection which randomly Dropout on the feature maps with the probabilities given by the attention map.
no code implementations • 31 Oct 2017 • Yuefu Zhou, Shanshan Huang, Ya zhang, Yan-Feng Wang
While minimizing the quantization loss guarantees that quantization has minimal effect on retrieval accuracy, it unfortunately significantly reduces the expressiveness of features even before the quantization.
no code implementations • ICCV 2017 • Yan Wang, Lingxi Xie, Chenxi Liu, Ya zhang, Wenjun Zhang, Alan Yuille
In this paper, we reveal the importance and benefits of introducing second-order operations into deep neural networks.
no code implementations • 3 Mar 2017 • Yan Wang, Lingxi Xie, Ya zhang, Wenjun Zhang, Alan Yuille
We formulate the function of a convolutional layer as learning a large visual vocabulary, and propose an alternative way, namely Deep Collaborative Learning (DCL), to reduce the computational complexity.
no code implementations • 28 Feb 2017 • Shanshan Huang, Yichao Xiong, Ya zhang, Jia Wang
Considering the difficulty in obtaining labeled datasets for image retrieval task in large scale, we propose a novel CNN-based unsupervised hashing method, namely Unsupervised Triplet Hashing (UTH).
no code implementations • CVPR 2016 • Shaoli Huang, Zhe Xu, DaCheng Tao, Ya zhang
In the context of fine-grained visual categorization, the ability to interpret models as human-understandable visual manuals is sometimes as important as achieving high classification accuracy.
Ranked #58 on
Fine-Grained Image Classification
on CUB-200-2011
no code implementations • ICCV 2015 • Zhe Xu, Shaoli Huang, Ya zhang, DaCheng Tao
We propose a new method for fine-grained object recognition that employs part-level annotations and deep convolutional neural networks (CNNs) in a unified framework.
no code implementations • 2014 IEEE International Conference on Data Mining 2015 • Ya Zhang, Yi Wei, Jianbiao Ren
With the ever enhanced capability to tracking advertisement and users' interaction with the advertisement, data-driven multi-touch attribution models, which attempt to infer the contribution from user interaction data, become an important research direction.