Search Results for author: Xian-Sheng Hua

Found 79 papers, 36 papers with code

Momentum Batch Normalization for Deep Learning with Small Batch Size

no code implementations ECCV 2020 Hongwei Yong, Jianqiang Huang, Deyu Meng, Xian-Sheng Hua, Lei Zhang

To make a deeper understanding of BN, in this work we prove that BN actually introduces a certain level of noise into the sample mean and variance during the training process, while the noise level depends only on the batch size.

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

2 code implementations11 May 2022 Yawei Li, Kai Zhang, Radu Timofte, Luc van Gool, Fangyuan Kong, Mingxi Li, Songwei Liu, Zongcai Du, Ding Liu, Chenhui Zhou, Jingyi Chen, Qingrui Han, Zheyuan Li, Yingqi Liu, Xiangyu Chen, Haoming Cai, Yu Qiao, Chao Dong, Long Sun, Jinshan Pan, Yi Zhu, Zhikai Zong, Xiaoxiao Liu, Zheng Hui, Tao Yang, Peiran Ren, Xuansong Xie, Xian-Sheng Hua, Yanbo Wang, Xiaozhong Ji, Chuming Lin, Donghao Luo, Ying Tai, Chengjie Wang, Zhizhong Zhang, Yuan Xie, Shen Cheng, Ziwei Luo, Lei Yu, Zhihong Wen, Qi Wu1, Youwei Li, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Yuanfei Huang, Meiguang Jin, Hua Huang, Jing Liu, Xinjian Zhang, Yan Wang, Lingshun Long, Gen Li, Yuanfan Zhang, Zuowei Cao, Lei Sun, Panaetov Alexander, Yucong Wang, Minjie Cai, Li Wang, Lu Tian, Zheyuan Wang, Hongbing Ma, Jie Liu, Chao Chen, Yidong Cai, Jie Tang, Gangshan Wu, Weiran Wang, Shirui Huang, Honglei Lu, Huan Liu, Keyan Wang, Jun Chen, Shi Chen, Yuchun Miao, Zimo Huang, Lefei Zhang, Mustafa Ayazoğlu, Wei Xiong, Chengyi Xiong, Fei Wang, Hao Li, Ruimian Wen, Zhijing Yang, Wenbin Zou, Weixin Zheng, Tian Ye, Yuncheng Zhang, Xiangzhen Kong, Aditya Arora, Syed Waqas Zamir, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Dandan Gaoand Dengwen Zhouand Qian Ning, Jingzhu Tang, Han Huang, YuFei Wang, Zhangheng Peng, Haobo Li, Wenxue Guan, Shenghua Gong, Xin Li, Jun Liu, Wanjun Wang, Dengwen Zhou, Kun Zeng, Hanjiang Lin, Xinyu Chen, Jinsheng Fang

The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.

Image Super-Resolution

Dense Learning based Semi-Supervised Object Detection

1 code implementation15 Apr 2022 Binghui Chen, Pengyu Li, Xiang Chen, Biao Wang, Lei Zhang, Xian-Sheng Hua

Semi-supervised object detection (SSOD) aims to facilitate the training and deployment of object detectors with the help of a large amount of unlabeled data.

Object Detection Semi-Supervised Object Detection

Spatial Likelihood Voting with Self-Knowledge Distillation for Weakly Supervised Object Detection

no code implementations14 Apr 2022 Ze Chen, Zhihang Fu, Jianqiang Huang, Mingyuan Tao, Rongxin Jiang, Xiang Tian, Yaowu Chen, Xian-Sheng Hua

The likelihood maps generated by the SLV module are used to supervise the feature learning of the backbone network, encouraging the network to attend to wider and more diverse areas of the image.

Multiple Instance Learning Region Proposal +2

Dynamic Supervisor for Cross-dataset Object Detection

no code implementations1 Apr 2022 Ze Chen, Zhihang Fu, Jianqiang Huang, Mingyuan Tao, Shengyu Li, Rongxin Jiang, Xiang Tian, Yaowu Chen, Xian-Sheng Hua

The application of cross-dataset training in object detection tasks is complicated because the inconsistency in the category range across datasets transforms fully supervised learning into semi-supervised learning.

Object Detection

Disentangled Representation Learning for Text-Video Retrieval

1 code implementation14 Mar 2022 Qiang Wang, Yanhao Zhang, Yun Zheng, Pan Pan, Xian-Sheng Hua

Cross-modality interaction is a critical component in Text-Video Retrieval (TVR), yet there has been little examination of how different influencing factors for computing interaction affect performance.

Ranked #2 on Video Retrieval on MSR-VTT-1kA (using extra training data)

Representation Learning Video Retrieval

Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation

1 code implementation2 Mar 2022 Zhaozheng Chen, Tan Wang, Xiongwei Wu, Xian-Sheng Hua, Hanwang Zhang, Qianru Sun

Specifically, due to the sum-over-class pooling nature of BCE, each pixel in CAM may be responsive to multiple classes co-occurring in the same receptive field.

Weakly-Supervised Semantic Segmentation

Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification

no code implementations15 Jan 2022 Menglin Wang, Jiachen Li, Baisheng Lai, Xiaojin Gong, Xian-Sheng Hua

Assisted with the camera-aware proxies, we design two proxy-level contrastive learning losses that are, respectively, based on offline and online association results.

Contrastive Learning Unsupervised Person Re-Identification

Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification

1 code implementation29 Dec 2021 Beier Zhu, Yulei Niu, Xian-Sheng Hua, Hanwang Zhang

We address the overlooked unbiasedness in existing long-tailed classification methods: we find that their overall improvement is mostly attributed to the biased preference of tail over head, as the test distribution is assumed to be balanced; however, when the test is as imbalanced as the long-tailed training data -- let the test respect Zipf's law of nature -- the tail bias is no longer beneficial overall because it hurts the head majorities.

Classification

Meta Clustering Learning for Large-scale Unsupervised Person Re-identification

no code implementations19 Nov 2021 Xin Jin, Tianyu He, Zhiheng Yin, Xu Shen, Tongliang Liu, Xinchao Wang, Jianqiang Huang, Xian-Sheng Hua, Zhibo Chen

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.

Unsupervised Person Re-Identification

Density-Based Clustering with Kernel Diffusion

no code implementations11 Oct 2021 Chao Zheng, Yingjie Chen, Chong Chen, Jianqiang Huang, Xian-Sheng Hua

Finding a suitable density function is essential for density-based clustering algorithms such as DBSCAN and DPC.

Face Clustering

On Non-Random Missing Labels in Semi-Supervised Learning

no code implementations ICLR 2022 Xinting Hu, Yulei Niu, Chunyan Miao, Xian-Sheng Hua, Hanwang Zhang

Semi-Supervised Learning (SSL) is fundamentally a missing label problem, in which the label Missing Not At Random (MNAR) problem is more realistic and challenging, compared to the widely-adopted yet naive Missing Completely At Random assumption where both labeled and unlabeled data share the same class distribution.

Imputation

Unleash the Potential of Adaptation Models via Dynamic Domain Labels

no code implementations29 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.

Domain Adaptation

Improving 3D Object Detection with Channel-wise Transformer

1 code implementation ICCV 2021 Hualian Sheng, Sijia Cai, YuAn Liu, Bing Deng, Jianqiang Huang, Xian-Sheng Hua, Min-Jian Zhao

Though 3D object detection from point clouds has achieved rapid progress in recent years, the lack of flexible and high-performance proposal refinement remains a great hurdle for existing state-of-the-art two-stage detectors.

3D Object Detection Region Proposal

Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth

no code implementations28 Jul 2021 Chenhang He, Jianqiang Huang, Xian-Sheng Hua, Lei Zhang

Current geometry-based monocular 3D object detection models can efficiently detect objects by leveraging perspective geometry, but their performance is limited due to the absence of accurate depth information.

Depth Estimation Monocular 3D Object Detection

Transporting Causal Mechanisms for Unsupervised Domain Adaptation

1 code implementation ICCV 2021 Zhongqi Yue, Qianru Sun, Xian-Sheng Hua, Hanwang Zhang

However, the theoretical solution provided by transportability is far from practical for UDA, because it requires the stratification and representation of the unobserved confounder that is the cause of the domain gap.

Unsupervised Domain Adaptation

Revisiting Knowledge Distillation: An Inheritance and Exploration Framework

1 code implementation CVPR 2021 Zhen Huang, Xu Shen, Jun Xing, Tongliang Liu, Xinmei Tian, Houqiang Li, Bing Deng, Jianqiang Huang, Xian-Sheng Hua

The inheritance part is learned with a similarity loss to transfer the existing learned knowledge from the teacher model to the student model, while the exploration part is encouraged to learn representations different from the inherited ones with a dis-similarity loss.

Knowledge Distillation

Interactive Self-Training With Mean Teachers for Semi-Supervised Object Detection

no code implementations CVPR 2021 Qize Yang, Xihan Wei, Biao Wang, Xian-Sheng Hua, Lei Zhang

Specifically, to alleviate the instability among the detection results in different iterations, we propose using nonmaximum suppression to fuse the detection results from different iterations.

Object Detection Semi-Supervised Object Detection

Criterion-based Heterogeneous Collaborative Filtering for Multi-behavior Implicit Recommendation

1 code implementation25 May 2021 Xiao Luo, Daqing Wu, Chong Chen, Jinwen Ma, Minghua Deng, Chen Shen, Jianqiang Huang, Xian-Sheng Hua

Besides, CHCF integrates criterion learning and user preference learning into a unified framework, which can be trained jointly for the interaction prediction on target behavior.

Collaborative Filtering Metric Learning +1

Attention-guided Temporally Coherent Video Object Matting

1 code implementation24 May 2021 Yunke Zhang, Chi Wang, Miaomiao Cui, Peiran Ren, Xuansong Xie, Xian-Sheng Hua, Hujun Bao, QiXing Huang, Weiwei Xu

Experimental results show that our method can generate high-quality alpha mattes for various videos featuring appearance change, occlusion, and fast motion.

Image Matting Semantic Segmentation +3

Graph Contrastive Clustering

1 code implementation ICCV 2021 Huasong Zhong, Jianlong Wu, Chong Chen, Jianqiang Huang, Minghua Deng, Liqiang Nie, Zhouchen Lin, Xian-Sheng Hua

On the other hand, a novel graph-based contrastive learning strategy is proposed to learn more compact clustering assignments.

Contrastive Learning

Half-Real Half-Fake Distillation for Class-Incremental Semantic Segmentation

no code implementations2 Apr 2021 Zilong Huang, Wentian Hao, Xinggang Wang, Mingyuan Tao, Jianqiang Huang, Wenyu Liu, Xian-Sheng Hua

Despite their success for semantic segmentation, convolutional neural networks are ill-equipped for incremental learning, \ie, adapting the original segmentation model as new classes are available but the initial training data is not retained.

Incremental Learning Semantic Segmentation

Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization

1 code implementation29 Mar 2021 Xin Jin, Tianyu He, Kecheng Zheng, Zhiheng Yin, Xu Shen, Zhen Huang, Ruoyu Feng, Jianqiang Huang, Xian-Sheng Hua, Zhibo Chen

Specifically, we introduce Gait recognition as an auxiliary task to drive the Image ReID model to learn cloth-agnostic representations by leveraging personal unique and cloth-independent gait information, we name this framework as GI-ReID.

Gait Recognition Person Re-Identification

Dense Interaction Learning for Video-based Person Re-identification

no code implementations ICCV 2021 Tianyu He, Xin Jin, Xu Shen, Jianqiang Huang, Zhibo Chen, Xian-Sheng Hua

The CNN encoder is responsible for efficiently extracting discriminative spatial features while the DI decoder is designed to densely model spatial-temporal inherent interaction across frames.

Video-Based Person Re-Identification

Distilling Causal Effect of Data in Class-Incremental Learning

1 code implementation CVPR 2021 Xinting Hu, Kaihua Tang, Chunyan Miao, Xian-Sheng Hua, Hanwang Zhang

We propose a causal framework to explain the catastrophic forgetting in Class-Incremental Learning (CIL) and then derive a novel distillation method that is orthogonal to the existing anti-forgetting techniques, such as data replay and feature/label distillation.

class-incremental learning Incremental Learning

Counterfactual Zero-Shot and Open-Set Visual Recognition

1 code implementation CVPR 2021 Zhongqi Yue, Tan Wang, Hanwang Zhang, Qianru Sun, Xian-Sheng Hua

We show that the key reason is that the generation is not Counterfactual Faithful, and thus we propose a faithful one, whose generation is from the sample-specific counterfactual question: What would the sample look like, if we set its class attribute to a certain class, while keeping its sample attribute unchanged?

Open Set Learning Zero-Shot Learning

VideoFlow: A Framework for Building Visual Analysis Pipelines

no code implementations1 Jan 2021 Yue Wu, Jianqiang Huang, Jiangjie Zhen, Guokun Wang, Chen Shen, Chang Zhou, Xian-Sheng Hua

The past years have witnessed an explosion of deep learning frameworks like PyTorch and TensorFlow since the success of deep neural networks.

Video Object Segmentation With Dynamic Memory Networks and Adaptive Object Alignment

1 code implementation ICCV 2021 Shuxian Liang, Xu Shen, Jianqiang Huang, Xian-Sheng Hua

In this paper, we propose a novel solution for object-matching based semi-supervised video object segmentation, where the target object masks in the first frame are provided.

Frame Semantic Segmentation +2

3D Local Convolutional Neural Networks for Gait Recognition

1 code implementation ICCV 2021 Zhen Huang, Dixiu Xue, Xu Shen, Xinmei Tian, Houqiang Li, Jianqiang Huang, Xian-Sheng Hua

Second, different body parts possess different scales, and even the same part in different frames can appear at different locations and scales.

Frame Gait Recognition

Learning to Generate Content-Aware Dynamic Detectors

no code implementations8 Dec 2020 Junyi Feng, Jiashen Hua, Baisheng Lai, Jianqiang Huang, Xi Li, Xian-Sheng Hua

To the best of our knowledge, our CADDet is the first work to introduce dynamic routing mechanism in object detection.

Object Detection

Tracklets Predicting Based Adaptive Graph Tracking

no code implementations18 Oct 2020 Chaobing Shan, Chunbo Wei, Bing Deng, Jianqiang Huang, Xian-Sheng Hua, Xiaoliang Cheng, Kewei Liang

It re-extracts the features of the tracklets in the current frame based on motion predicting, which is the key to solve the problem of features inconsistent.

Autonomous Driving Frame +2

CIMON: Towards High-quality Hash Codes

no code implementations15 Oct 2020 Xiao Luo, Daqing Wu, Zeyu Ma, Chong Chen, Minghua Deng, Jinwen Ma, Zhongming Jin, Jianqiang Huang, Xian-Sheng Hua

However, due to the inefficient representation ability of the pre-trained model, many false positives and negatives in local semantic similarity will be introduced and lead to error propagation during the hash code learning.

Image Augmentation Semantic Similarity +1

Interventional Few-Shot Learning

1 code implementation NeurIPS 2020 Zhongqi Yue, Hanwang Zhang, Qianru Sun, Xian-Sheng Hua

Specifically, we develop three effective IFSL algorithmic implementations based on the backdoor adjustment, which is essentially a causal intervention towards the SCM of many-shot learning: the upper-bound of FSL in a causal view.

Few-Shot Learning

PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation

1 code implementation2 Sep 2020 Shaotian Yan, Chen Shen, Zhongming Jin, Jianqiang Huang, Rongxin Jiang, Yaowu Chen, Xian-Sheng Hua

Today, scene graph generation(SGG) task is largely limited in realistic scenarios, mainly due to the extremely long-tailed bias of predicate annotation distribution.

Graph Generation Unbiased Scene Graph Generation

Apparel-invariant Feature Learning for Apparel-changed Person Re-identification

no code implementations14 Aug 2020 Zhengxu Yu, Yilun Zhao, Bin Hong, Zhongming Jin, Jianqiang Huang, Deng Cai, Xiaofei He, Xian-Sheng Hua

Therefore, it is critical to learn an apparel-invariant person representation under cases like cloth changing or several persons wearing similar clothes.

Person Re-Identification Representation Learning

Deep Robust Clustering by Contrastive Learning

1 code implementation7 Aug 2020 Huasong Zhong, Chong Chen, Zhongming Jin, Xian-Sheng Hua

Different from existing methods, DRC looks into deep clustering from two perspectives of both semantic clustering assignment and representation feature, which can increase inter-class diversities and decrease intra-class diversities simultaneously.

Contrastive Learning Data Augmentation +1

Salvage Reusable Samples from Noisy Data for Robust Learning

1 code implementation6 Aug 2020 Zeren Sun, Xian-Sheng Hua, Yazhou Yao, Xiu-Shen Wei, Guosheng Hu, Jian Zhang

To this end, we propose a certainty-based reusable sample selection and correction approach, termed as CRSSC, for coping with label noise in training deep FG models with web images.

Out-of-distribution Generalization via Partial Feature Decorrelation

no code implementations30 Jul 2020 Xin Guo, Zhengxu Yu, Chao Xiang, Zhongming Jin, Jianqiang Huang, Deng Cai, Xiaofei He, Xian-Sheng Hua

Most deep-learning-based image classification methods assume that all samples are generated under an independent and identically distributed (IID) setting.

Classification General Classification +3

Joint Auction-Coalition Formation Framework for Communication-Efficient Federated Learning in UAV-Enabled Internet of Vehicles

no code implementations13 Jul 2020 Jer Shyuan Ng, Wei Yang Bryan Lim, Hong-Ning Dai, Zehui Xiong, Jianqiang Huang, Dusit Niyato, Xian-Sheng Hua, Cyril Leung, Chunyan Miao

The simulation results show that the grand coalition, where all UAVs join a single coalition, is not always stable due to the profit-maximizing behavior of the UAVs.

Networking and Internet Architecture Signal Processing

Adversarial Mutual Information for Text Generation

1 code implementation ICML 2020 Boyuan Pan, Yazheng Yang, Kaizhao Liang, Bhavya Kailkhura, Zhongming Jin, Xian-Sheng Hua, Deng Cai, Bo Li

Recent advances in maximizing mutual information (MI) between the source and target have demonstrated its effectiveness in text generation.

Text Generation

SLV: Spatial Likelihood Voting for Weakly Supervised Object Detection

no code implementations CVPR 2020 Ze Chen, Zhihang Fu, Rongxin Jiang, Yaowu Chen, Xian-Sheng Hua

In this paper, we propose a spatial likelihood voting (SLV) module to converge the proposal localizing process without any bounding box annotations.

General Classification Multiple Instance Learning +2

Counterfactual VQA: A Cause-Effect Look at Language Bias

1 code implementation CVPR 2021 Yulei Niu, Kaihua Tang, Hanwang Zhang, Zhiwu Lu, Xian-Sheng Hua, Ji-Rong Wen

VQA models may tend to rely on language bias as a shortcut and thus fail to sufficiently learn the multi-modal knowledge from both vision and language.

Counterfactual Inference Question Answering +2

Towards Fine-grained Human Pose Transfer with Detail Replenishing Network

no code implementations26 May 2020 Lingbo Yang, Pan Wang, Chang Liu, Zhanning Gao, Peiran Ren, Xinfeng Zhang, Shanshe Wang, Siwei Ma, Xian-Sheng Hua, Wen Gao

Human pose transfer (HPT) is an emerging research topic with huge potential in fashion design, media production, online advertising and virtual reality.

14 Pose Transfer

PyRetri: A PyTorch-based Library for Unsupervised Image Retrieval by Deep Convolutional Neural Networks

1 code implementation2 May 2020 Benyi Hu, Ren-Jie Song, Xiu-Shen Wei, Yazhou Yao, Xian-Sheng Hua, Yuehu Liu

Despite significant progress of applying deep learning methods to the field of content-based image retrieval, there has not been a software library that covers these methods in a unified manner.

Content-Based Image Retrieval

Boosting Semantic Human Matting with Coarse Annotations

no code implementations CVPR 2020 Jinlin Liu, Yuan YAO, Wendi Hou, Miaomiao Cui, Xuansong Xie, Chang-Shui Zhang, Xian-Sheng Hua

In this paper, we propose to use coarse annotated data coupled with fine annotated data to boost end-to-end semantic human matting without trimaps as extra input.

Image Matting Semantic Segmentation

Towards Federated Learning in UAV-Enabled Internet of Vehicles: A Multi-Dimensional Contract-Matching Approach

no code implementations8 Apr 2020 Wei Yang Bryan Lim, Jianqiang Huang, Zehui Xiong, Jiawen Kang, Dusit Niyato, Xian-Sheng Hua, Cyril Leung, Chunyan Miao

Coupled with the rise of Deep Learning, the wealth of data and enhanced computation capabilities of Internet of Vehicles (IoV) components enable effective Artificial Intelligence (AI) based models to be built.

Signal Processing Networking and Internet Architecture

Gradient Centralization: A New Optimization Technique for Deep Neural Networks

7 code implementations ECCV 2020 Hongwei Yong, Jianqiang Huang, Xian-Sheng Hua, Lei Zhang

It has been shown that using the first and second order statistics (e. g., mean and variance) to perform Z-score standardization on network activations or weight vectors, such as batch normalization (BN) and weight standardization (WS), can improve the training performance.

Fine-Grained Image Classification General Classification

CPR-GCN: Conditional Partial-Residual Graph Convolutional Network in Automated Anatomical Labeling of Coronary Arteries

no code implementations CVPR 2020 Han Yang, Xingjian Zhen, Ying Chi, Lei Zhang, Xian-Sheng Hua

On the technical side, the Partial-Residual GCN takes the position features of the branches, with the 3D spatial image features as conditions, to predict the label for each branches.

A Survey on Deep Hashing Methods

no code implementations4 Mar 2020 Xiao Luo, Haixin Wang, Daqing Wu, Chong Chen, Minghua Deng, Jianqiang Huang, Xian-Sheng Hua

Nearest neighbor search aims to obtain the samples in the database with the smallest distances from them to the queries, which is a basic task in a range of fields, including computer vision and data mining.

Domain Adaptation Quantization +2

Towards Precise Intra-camera Supervised Person Re-identification

no code implementations12 Feb 2020 Menglin Wang, Baisheng Lai, Haokun Chen, Jianqiang Huang, Xiaojin Gong, Xian-Sheng Hua

Our approach performs even comparable to state-of-the-art fully supervised methods in two of the datasets.

Person Re-Identification

Towards a Fast Steady-State Visual Evoked Potentials (SSVEP) Brain-Computer Interface (BCI)

no code implementations4 Feb 2020 Aung Aung Phyo Wai, Yangsong Zhang, Heng Guo, Ying Chi, Lei Zhang, Xian-Sheng Hua, Seong Whan Lee, Cuntai Guan

We observed that CSTA achieves the maximum mean accuracy of 97. 43$\pm$2. 26 % and 85. 71$\pm$13. 41 % with four-class and forty-class SSVEP data-sets respectively in sub-second response time in offline analysis.

HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptation

1 code implementation27 Dec 2019 Chao Chen, Zhihang Fu, Zhihong Chen, Sheng Jin, Zhaowei Cheng, Xinyu Jin, Xian-Sheng Hua

In particular, our proposed HoMM can perform arbitrary-order moment tensor matching, we show that the first-order HoMM is equivalent to Maximum Mean Discrepancy (MMD) and the second-order HoMM is equivalent to Correlation Alignment (CORAL).

Unsupervised Domain Adaptation

Quantization Networks

1 code implementation CVPR 2019 Jiwei Yang, Xu Shen, Jun Xing, Xinmei Tian, Houqiang Li, Bing Deng, Jianqiang Huang, Xian-Sheng Hua

The proposed quantization function can be learned in a lossless and end-to-end manner and works for any weights and activations of neural networks in a simple and uniform way.

Image Classification Object Detection +1

SSAH: Semi-supervised Adversarial Deep Hashing with Self-paced Hard Sample Generation

no code implementations20 Nov 2019 Sheng Jin, Shangchen Zhou, Yao Liu, Chao Chen, Xiaoshuai Sun, Hongxun Yao, Xian-Sheng Hua

In this paper, we propose a novel Semi-supervised Self-pace Adversarial Hashing method, named SSAH to solve the above problems in a unified framework.

Progressive Transfer Learning

1 code implementation7 Aug 2019 Zhengxu Yu, Dong Shen, Zhongming Jin, Jianqiang Huang, Deng Cai, Xian-Sheng Hua

Model fine-tuning is a widely used transfer learning approach in person Re-identification (ReID) applications, which fine-tuning a pre-trained feature extraction model into the target scenario instead of training a model from scratch.

Image Classification Person Re-Identification +1

Extracting Visual Knowledge from the Internet: Making Sense of Image Data

no code implementations7 Jun 2019 Yazhou Yao, Jian Zhang, Xian-Sheng Hua, Fumin Shen, Zhenmin Tang

Recent successes in visual recognition can be primarily attributed to feature representation, learning algorithms, and the ever-increasing size of labeled training data.

Representation Learning

Automated Segmentation of Pulmonary Lobes using Coordination-Guided Deep Neural Networks

2 code implementations19 Apr 2019 Wenjia Wang, Junxuan Chen, Jie Zhao, Ying Chi, Xuansong Xie, Li Zhang, Xian-Sheng Hua

The proposed model is trained and evaluated on a few publicly available datasets and has achieved the state-of-the-art accuracy with a mean Dice coefficient index of 0. 947 $\pm$ 0. 044.

Towards Self-similarity Consistency and Feature Discrimination for Unsupervised Domain Adaptation

no code implementations13 Apr 2019 Chao Chen, Zhihang Fu, Zhihong Chen, Zhaowei Cheng, Xinyu Jin, Xian-Sheng Hua

Recent advances in unsupervised domain adaptation mainly focus on learning shared representations by global distribution alignment without considering class information across domains.

Unsupervised Domain Adaptation

Deep Active Learning for Video-based Person Re-identification

no code implementations14 Dec 2018 Menglin Wang, Baisheng Lai, Zhongming Jin, Xiaojin Gong, Jianqiang Huang, Xian-Sheng Hua

With the gained annotations of the actively selected candidates, the tracklets' pesudo labels are updated by label merging and further used to re-train our re-ID model.

Active Learning Video-Based Person Re-Identification

Dynamic Spatio-temporal Graph-based CNNs for Traffic Prediction

no code implementations5 Dec 2018 Ken Chen, Fei Chen, Baisheng Lai, Zhongming Jin, Yong liu, Kai Li, Long Wei, Pengfei Wang, Yandong Tang, Jianqiang Huang, Xian-Sheng Hua

To capture the graph dynamics, we use the graph prediction stream to predict the dynamic graph structures, and the predicted structures are fed into the flow prediction stream.

Traffic Prediction

An Adversarial Approach to Hard Triplet Generation

no code implementations ECCV 2018 Yiru Zhao, Zhongming Jin, Guo-Jun Qi, Hongtao Lu, Xian-Sheng Hua

While deep neural networks have demonstrated competitive results for many visual recognition and image retrieval tasks, the major challenge lies in distinguishing similar images from different categories (i. e., hard negative examples) while clustering images with large variations from the same category (i. e., hard positive examples).

Image Retrieval

Deep Saliency Hashing

no code implementations4 Jul 2018 Sheng Jin, Hongxun Yao, Xiaoshuai Sun, Shangchen Zhou, Lei Zhang, Xian-Sheng Hua

As the core of DSaH, the saliency loss guides the attention network to mine discriminative regions from pairs of images.

Quantization

Sharp Attention Network via Adaptive Sampling for Person Re-identification

no code implementations7 May 2018 Chen Shen, Guo-Jun Qi, Rongxin Jiang, Zhongming Jin, Hongwei Yong, Yaowu Chen, Xian-Sheng Hua

In this paper, we present novel sharp attention networks by adaptively sampling feature maps from convolutional neural networks (CNNs) for person re-identification (re-ID) problem.

Person Re-Identification

Homocentric Hypersphere Feature Embedding for Person Re-identification

no code implementations24 Apr 2018 Wangmeng Xiang, Jianqiang Huang, Xianbiao Qi, Xian-Sheng Hua, Lei Zhang

Person re-identification (Person ReID) is a challenging task due to the large variations in camera viewpoint, lighting, resolution, and human pose.

Person Re-Identification

Video2Shop: Exact Matching Clothes in Videos to Online Shopping Images

1 code implementation CVPR 2017 Zhi-Qi Cheng, Xiao Wu, Yang Liu, Xian-Sheng Hua

For the video side, deep visual features are extracted from detected object regions in each frame, and further fed into a Long Short-Term Memory (LSTM) framework for sequence modeling, which captures the temporal dynamics in videos.

Frame

Global versus Localized Generative Adversarial Nets

2 code implementations CVPR 2018 Guo-Jun Qi, Liheng Zhang, Hao Hu, Marzieh Edraki, Jingdong Wang, Xian-Sheng Hua

In this paper, we present a novel localized Generative Adversarial Net (GAN) to learn on the manifold of real data.

General Classification

Refining Image Categorization by Exploiting Web Images and General Corpus

no code implementations16 Mar 2017 Yazhou Yao, Jian Zhang, Fumin Shen, Xian-Sheng Hua, Wankou Yang, Zhenmin Tang

To tackle these problems, in this work, we exploit general corpus information to automatically select and subsequently classify web images into semantic rich (sub-)categories.

Image Categorization

Exploiting Web Images for Dataset Construction: A Domain Robust Approach

no code implementations22 Nov 2016 Yazhou Yao, Jian Zhang, Fumin Shen, Xian-Sheng Hua, Jingsong Xu, Zhenmin Tang

To reduce the cost of manual labelling, there has been increased research interest in automatically constructing image datasets by exploiting web images.

Domain Adaptation Image Classification +1

Deep CTR Prediction in Display Advertising

no code implementations20 Sep 2016 Junxuan Chen, Baigui Sun, Hao Li, Hongtao Lu, Xian-Sheng Hua

Click through rate (CTR) prediction of image ads is the core task of online display advertising systems, and logistic regression (LR) has been frequently applied as the prediction model.

Click-Through Rate Prediction

Hybrid Affinity Propagation

no code implementations30 Jul 2013 Jingdong Wang, Hao Xu, Xian-Sheng Hua, Shipeng Li

We formulate this problem as finding a few image exemplars to represent the image set semantically and visually, and solve it in a hybrid way by exploiting both visual and textual information associated with images.

Cannot find the paper you are looking for? You can Submit a new open access paper.