Search Results for author: Xiaojun Chang

Found 76 papers, 20 papers with code

Mining Inter-Video Proposal Relations for Video Object Detection

1 code implementation ECCV 2020 Mingfei Han, Yali Wang, Xiaojun Chang, Yu Qiao

Recent studies have shown that, context aggregating information from proposals in different frames can clearly enhance the performance of video object detection.

Video Object Detection

Towards Explanation for Unsupervised Graph-Level Representation Learning

no code implementations20 May 2022 Qinghua Zheng, Jihong Wang, Minnan Luo, YaoLiang Yu, Jundong Li, Lina Yao, Xiaojun Chang

Due to the superior performance of Graph Neural Networks (GNNs) in various domains, there is an increasing interest in the GNN explanation problem "\emph{which fraction of the input graph is the most crucial to decide the model's decision?}"

Decision Making Graph Classification +2

PRE-NAS: Predictor-assisted Evolutionary Neural Architecture Search

no code implementations27 Apr 2022 Yameng Peng, Andy Song, Vic Ciesielski, Haytham M. Fayek, Xiaojun Chang

This often requires a high computational overhead to evaluate a number of candidate networks from the set of all possible networks in the search space during the search.

Neural Architecture Search

Automated Progressive Learning for Efficient Training of Vision Transformers

1 code implementation28 Mar 2022 Changlin Li, Bohan Zhuang, Guangrun Wang, Xiaodan Liang, Xiaojun Chang, Yi Yang

First, we develop a strong manual baseline for progressive learning of ViTs, by introducing momentum growth (MoGrow) to bridge the gap brought by model growth.

Beyond Fixation: Dynamic Window Visual Transformer

1 code implementation24 Mar 2022 Pengzhen Ren, Changlin Li, Guangrun Wang, Yun Xiao, Qing Du, Xiaodan Liang, Xiaojun Chang

Recently, a surge of interest in visual transformers is to reduce the computational cost by limiting the calculation of self-attention to a local window.

Exploring Inter-Channel Correlation for Diversity-preserved KnowledgeDistillation

1 code implementation8 Feb 2022 Li Liu, Qingle Huang, Sihao Lin, Hongwei Xie, Bing Wang, Xiaojun Chang, Xiaodan Liang

Extensive experiments on two vision tasks, includ-ing ImageNet classification and Pascal VOC segmentation, demonstrate the superiority of our ICKD, which consis-tently outperforms many existing methods, advancing thestate-of-the-art in the fields of Knowledge Distillation.

Knowledge Distillation

Balancing Generalization and Specialization in Zero-shot Learning

no code implementations6 Jan 2022 Yun Li, Zhe Liu, Lina Yao, Xiaojun Chang

In this paper, we propose an end-to-end network with balanced generalization and specialization abilities, termed as BGSNet, to take advantage of both abilities, and balance them at instance- and dataset-level.

Meta-Learning Network Pruning +1

BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule

no code implementations25 Nov 2021 Miao Zhang, Jilin Hu, Steven Su, Shirui Pan, Xiaojun Chang, Bin Yang, Gholamreza Haffari

Differentiable Architecture Search (DARTS) has received massive attention in recent years, mainly because it significantly reduces the computational cost through weight sharing and continuous relaxation.

Neural Architecture Search Variational Inference

An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning

no code implementations3 Nov 2021 Yun Li, Zhe Liu, Lina Yao, Xianzhi Wang, Julian McAuley, Xiaojun Chang

Zero-Shot Learning (ZSL) aims to transfer learned knowledge from observed classes to unseen classes via semantic correlations.

Generalized Zero-Shot Learning

Signature-Graph Networks

no code implementations22 Oct 2021 Ali Hamdi, Flora Salim, Du Yong Kim, Xiaojun Chang

SGN constructs unique undirected graphs for each image based on the CNN feature maps.

Image Classification Representation Learning

Dynamic Slimmable Denoising Network

no code implementations17 Oct 2021 Zutao Jiang, Changlin Li, Xiaojun Chang, Jihua Zhu, Yi Yang

Here, we present dynamic slimmable denoising network (DDS-Net), a general method to achieve good denoising quality with less computational complexity, via dynamically adjusting the channel configurations of networks at test time with respect to different noisy images.

Fairness Image Denoising

Active Learning for Deep Visual Tracking

no code implementations17 Oct 2021 Di Yuan, Xiaojun Chang, Yi Yang, Qiao Liu, Dehua Wang, Zhenyu He

In this paper, we propose an active learning method for deep visual tracking, which selects and annotates the unlabeled samples to train the deep CNNs model.

Active Learning Visual Tracking

Reliable Shot Identification for Complex Event Detection via Visual-Semantic Embedding

no code implementations12 Oct 2021 Minnan Luo, Xiaojun Chang, Chen Gong

In this paper, we decompose the video into several segments and intuitively model the task of complex event detection as a multiple instance learning problem by representing each video as a "bag" of segments in which each segment is referred to as an instance.

Event Detection Multiple Instance Learning

Role Diversity Matters: A Study of Cooperative Training Strategies for Multi-Agent RL

no code implementations29 Sep 2021 Siyi Hu, Chuanlong Xie, Xiaodan Liang, Xiaojun Chang

In addition, role diversity can help to find a better training strategy and increase performance in cooperative MARL.

SMAC Starcraft +1

DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers

1 code implementation21 Sep 2021 Changlin Li, Guangrun Wang, Bing Wang, Xiaodan Liang, Zhihui Li, Xiaojun Chang

Dynamic networks have shown their promising capability in reducing theoretical computation complexity by adapting their architectures to the input during inference.

Fairness Model Compression

Semantics-Guided Contrastive Network for Zero-Shot Object detection

no code implementations4 Sep 2021 Caixia Yan, Xiaojun Chang, Minnan Luo, Huan Liu, Xiaoqin Zhang, Qinghua Zheng

To address these issues, we develop a novel Semantics-Guided Contrastive Network for ZSD, named ContrastZSD, a detection framework that first brings contrastive learning mechanism into the realm of zero-shot detection.

Contrastive Learning Zero-Shot Object Detection

Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions

no code implementations1 Sep 2021 Xiangtan Lin, Pengzhen Ren, Chung-Hsing Yeh, Lina Yao, Andy Song, Xiaojun Chang

Therefore, comprehensive surveys on this topic are essential to summarise challenges and solutions to foster future research.

Unsupervised Person Re-Identification

Legislator Representation Learning with Social Context and Expert Knowledge

no code implementations9 Aug 2021 Shangbin Feng, Zhaoxuan Tan, Zilong Chen, Peisheng Yu, Qinghua Zheng, Xiaojun Chang, Minnan Luo

Modeling the ideological perspectives of political actors is an essential task in computational political science with applications in many downstream tasks.

Representation Learning Stance Detection

Deep Learning for Embodied Vision Navigation: A Survey

no code implementations7 Jul 2021 Fengda Zhu, Yi Zhu, Vincent CS Lee, Xiaodan Liang, Xiaojun Chang

A navigation agent is supposed to have various intelligent skills, such as visual perceiving, mapping, planning, exploring and reasoning, etc.

Autonomous Driving Visual Navigation

Differentiable Architecture Search Meets Network Pruning at Initialization: A More Reliable, Efficient, and Flexible Framework

no code implementations22 Jun 2021 Miao Zhang, Steven Su, Shirui Pan, Xiaojun Chang, Wei Huang, Bin Yang, Gholamreza Haffari

Although Differentiable ARchiTecture Search (DARTS) has become the mainstream paradigm in Neural Architecture Search (NAS) due to its simplicity and efficiency, more recent works found that the performance of the searched architecture barely increases with the optimization proceeding in DARTS, and the final magnitudes obtained by DARTS could hardly indicate the importance of operations.

Network Pruning Neural Architecture Search

iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients

1 code implementation21 Jun 2021 Miao Zhang, Steven Su, Shirui Pan, Xiaojun Chang, Ehsan Abbasnejad, Reza Haffari

A key challenge to the scalability and quality of the learned architectures is the need for differentiating through the inner-loop optimisation.

Neural Architecture Search

Person Search Challenges and Solutions: A Survey

no code implementations1 May 2021 Xiangtan Lin, Pengzhen Ren, Yun Xiao, Xiaojun Chang, Alex Hauptmann

This paper surveyed the recent works on image-based and text-based person search from the perspective of challenges and solutions.

Person Search Text based Person Search

Attribute-Modulated Generative Meta Learning for Zero-Shot Classification

no code implementations22 Apr 2021 Yun Li, Zhe Liu, Lina Yao, Xiaojun Chang

The promising strategies for ZSL are to synthesize visual features of unseen classes conditioned on semantic side information and to incorporate meta-learning to eliminate the model's inherent bias towards seen classes.

Classification General Classification +4

SOON: Scenario Oriented Object Navigation with Graph-based Exploration

no code implementations CVPR 2021 Fengda Zhu, Xiwen Liang, Yi Zhu, Xiaojun Chang, Xiaodan Liang

In this task, an agent is required to navigate from an arbitrary position in a 3D embodied environment to localize a target following a scene description.

Visual Navigation

Dynamic Slimmable Network

1 code implementation CVPR 2021 Changlin Li, Guangrun Wang, Bing Wang, Xiaodan Liang, Zhihui Li, Xiaojun Chang

Here, we explore a dynamic network slimming regime, named Dynamic Slimmable Network (DS-Net), which aims to achieve good hardware-efficiency via dynamically adjusting filter numbers of networks at test time with respect to different inputs, while keeping filters stored statically and contiguously in hardware to prevent the extra burden.

Fairness Model Compression

BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search

1 code implementation ICCV 2021 Changlin Li, Tao Tang, Guangrun Wang, Jiefeng Peng, Bing Wang, Xiaodan Liang, Xiaojun Chang

In this work, we present Block-wisely Self-supervised Neural Architecture Search (BossNAS), an unsupervised NAS method that addresses the problem of inaccurate architecture rating caused by large weight-sharing space and biased supervision in previous methods.

Image Classification Neural Architecture Search

A Comprehensive Survey of Scene Graphs: Generation and Application

no code implementations17 Mar 2021 Xiaojun Chang, Pengzhen Ren, Pengfei Xu, Zhihui Li, Xiaojiang Chen, Alex Hauptmann

For example, given an image, we want to not only detect and recognize objects in the image, but also know the relationship between objects (visual relationship detection), and generate a text description (image captioning) based on the image content.

Image Captioning Question Answering +4

NAS-TC: Neural Architecture Search on Temporal Convolutions for Complex Action Recognition

no code implementations17 Mar 2021 Pengzhen Ren, Gang Xiao, Xiaojun Chang, Yun Xiao, Zhihui Li, Xiaojiang Chen

Accordingly, because of the automated design of its network structure, Neural architecture search (NAS) has achieved great success in the image processing field and attracted substantial research attention in recent years.

Action Recognition Action Recognition In Videos +2

UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers

1 code implementation20 Jan 2021 Siyi Hu, Fengda Zhu, Xiaojun Chang, Xiaodan Liang

Recent advances in multi-agent reinforcement learning have been largely limited in training one model from scratch for every new task.

reinforcement-learning SMAC

EXPLORING VULNERABILITIES OF BERT-BASED APIS

no code implementations1 Jan 2021 Xuanli He, Lingjuan Lyu, Lichao Sun, Xiaojun Chang, Jun Zhao

We then demonstrate how the extracted model can be exploited to develop effective attribute inference attack to expose sensitive information of the training data.

Inference Attack Model extraction +2

UPDeT: Universal Multi-agent RL via Policy Decoupling with Transformers

no code implementations ICLR 2021 Siyi Hu, Fengda Zhu, Xiaojun Chang, Xiaodan Liang

Recent advances in multi-agent reinforcement learning have been largely limited in training one model from scratch for every new task.

reinforcement-learning SMAC

Exploring Inter-Channel Correlation for Diversity-Preserved Knowledge Distillation

1 code implementation ICCV 2021 Li Liu, Qingle Huang, Sihao Lin, Hongwei Xie, Bing Wang, Xiaojun Chang, Xiaodan Liang

Extensive experiments on two vision tasks, including ImageNet classification and Pascal VOC segmentation, demonstrate the superiority of our ICKD, which consistently outperforms many existing methods, advancing the state-of-the-art in the fields of Knowledge Distillation.

Knowledge Distillation

Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement

1 code implementation NeurIPS 2020 Miao Zhang, Huiqi Li, Shirui Pan, Xiaojun Chang, ZongYuan Ge, Steven Su

A probabilistic exploration enhancement method is accordingly devised to encourage intelligent exploration during the architecture search in the latent space, to avoid local optimal in architecture search.

Bilevel Optimization Neural Architecture Search

Hierarchical Neural Architecture Search for Deep Stereo Matching

1 code implementation NeurIPS 2020 Xuelian Cheng, Yiran Zhong, Mehrtash Harandi, Yuchao Dai, Xiaojun Chang, Tom Drummond, Hongdong Li, ZongYuan Ge

To reduce the human efforts in neural network design, Neural Architecture Search (NAS) has been applied with remarkable success to various high-level vision tasks such as classification and semantic segmentation.

Neural Architecture Search Semantic Segmentation +2

Self-Weighted Robust LDA for Multiclass Classification with Edge Classes

no code implementations24 Sep 2020 Caixia Yan, Xiaojun Chang, Minnan Luo, Qinghua Zheng, Xiaoqin Zhang, Zhihui Li, Feiping Nie

In this regard, a novel self-weighted robust LDA with l21-norm based pairwise between-class distance criterion, called SWRLDA, is proposed for multi-class classification especially with edge classes.

Classification General Classification +1

Accurate Bounding-box Regression with Distance-IoU Loss for Visual Tracking

no code implementations3 Jul 2020 Di Yuan, Xiu Shu, Nana Fan, Xiaojun Chang, Qiao Liu, Zhenyu He

Moreover, we introduce a classification part that is trained online and optimized with a Conjugate-Gradient-based strategy to guarantee real-time tracking speed.

Visual Tracking

Multi-view Drone-based Geo-localization via Style and Spatial Alignment

no code implementations23 Jun 2020 Siyi Hu, Xiaojun Chang

In this paper, we focus on the task of multi-view multi-source geo-localization, which serves as an important auxiliary method of GPS positioning by matching drone-view image and satellite-view image with pre-annotated GPS tag.

TAG

Auxiliary Signal-Guided Knowledge Encoder-Decoder for Medical Report Generation

no code implementations6 Jun 2020 Mingjie Li, Fuyu Wang, Xiaojun Chang, Xiaodan Liang

Firstly, the regions of primary interest to radiologists are usually located in a small area of the global image, meaning that the remainder parts of the image could be considered as irrelevant noise in the training procedure.

Image Captioning Medical Report Generation +1

A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions

no code implementations1 Jun 2020 Pengzhen Ren, Yun Xiao, Xiaojun Chang, Po-Yao Huang, Zhihui Li, Xiaojiang Chen, Xin Wang

Neural Architecture Search (NAS) is just such a revolutionary algorithm, and the related research work is complicated and rich.

Neural Architecture Search

Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks

3 code implementations24 May 2020 Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, Xiaojun Chang, Chengqi Zhang

Modeling multivariate time series has long been a subject that has attracted researchers from a diverse range of fields including economics, finance, and traffic.

Graph Learning Multivariate Time Series Forecasting +2

Vision-Dialog Navigation by Exploring Cross-modal Memory

1 code implementation CVPR 2020 Yi Zhu, Fengda Zhu, Zhaohuan Zhan, Bingqian Lin, Jianbin Jiao, Xiaojun Chang, Xiaodan Liang

Benefiting from the collaborative learning of the L-mem and the V-mem, our CMN is able to explore the memory about the decision making of historical navigation actions which is for the current step.

Decision Making

ZSTAD: Zero-Shot Temporal Activity Detection

no code implementations CVPR 2020 Lingling Zhang, Xiaojun Chang, Jun Liu, Minnan Luo, Sen Wang, ZongYuan Ge, Alexander Hauptmann

An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos.

Action Detection Activity Detection

Unity Style Transfer for Person Re-Identification

no code implementations CVPR 2020 Chong Liu, Xiaojun Chang, Yi-Dong Shen

To solve this problem, we propose a UnityStyle adaption method, which can smooth the style disparities within the same camera and across different cameras.

Person Re-Identification Style Transfer +1

Blockwisely Supervised Neural Architecture Search with Knowledge Distillation

1 code implementation29 Nov 2019 Changlin Li, Jiefeng Peng, Liuchun Yuan, Guangrun Wang, Xiaodan Liang, Liang Lin, Xiaojun Chang

Moreover, we find that the knowledge of a network model lies not only in the network parameters but also in the network architecture.

 Ranked #1 on Neural Architecture Search on CIFAR-100 (Top-1 Error Rate metric)

Knowledge Distillation Neural Architecture Search

Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks

no code implementations CVPR 2020 Fengda Zhu, Yi Zhu, Xiaojun Chang, Xiaodan Liang

In this paper, we introduce Auxiliary Reasoning Navigation (AuxRN), a framework with four self-supervised auxiliary reasoning tasks to take advantage of the additional training signals derived from the semantic information.

Vision-Language Navigation

Multi-Head Attention with Diversity for Learning Grounded Multilingual Multimodal Representations

no code implementations IJCNLP 2019 Po-Yao Huang, Xiaojun Chang, Alexander Hauptmann

With the aim of promoting and understanding the multilingual version of image search, we leverage visual object detection and propose a model with diverse multi-head attention to learn grounded multilingual multimodal representations.

Image Retrieval Object Detection +1

Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correction

no code implementations21 Jun 2019 Fengda Zhu, Xiaojun Chang, Runhao Zeng, Mingkui Tan

We first develop an unsupervised diversity exploration method to learn task-specific skills using an unsupervised objective.

Autonomous Driving Continuous Control +1

Ensemble Teaching for Hybrid Label Propagation

no code implementations8 Apr 2019 Chen Gong, DaCheng Tao, Xiaojun Chang, Jian Yang

More importantly, HyDEnT conducts propagation under the guidance of an ensemble of teachers.

MMALFM: Explainable Recommendation by Leveraging Reviews and Images

no code implementations12 Nov 2018 Zhiyong Cheng, Xiaojun Chang, Lei Zhu, Rose C. Kanjirathinkal, Mohan Kankanhalli

Then the aspect importance is integrated into a novel aspect-aware latent factor model (ALFM), which learns user's and item's latent factors based on ratings.

RCAA: Relational Context-Aware Agents for Person Search

no code implementations ECCV 2018 Xiaojun Chang, Po-Yao Huang, Yi-Dong Shen, Xiaodan Liang, Yi Yang, Alexander G. Hauptmann

In this paper, we address this problem by training relational context-aware agents which learn the actions to localize the target person from the gallery of whole scene images.

Person Search

Multi-shot Person Re-identification through Set Distance with Visual Distributional Representation

no code implementations3 Aug 2018 Ting-yao Hu, Xiaojun Chang, Alexander G. Hauptmann

In this work, we propose the idea of visual distributional representation, which interprets an image set as samples drawn from an unknown distribution in appearance feature space.

Person Re-Identification

Reinforcement Cutting-Agent Learning for Video Object Segmentation

no code implementations CVPR 2018 Junwei Han, Le Yang, Dingwen Zhang, Xiaojun Chang, Xiaodan Liang

In this paper, we formulate this problem as a Markov Decision Process, where agents are learned to segment object regions under a deep reinforcement learning framework.

Decision Making Semantic Segmentation +3

Complex Event Detection by Identifying Reliable Shots From Untrimmed Videos

no code implementations ICCV 2017 Hehe Fan, Xiaojun Chang, De Cheng, Yi Yang, Dong Xu, Alexander G. Hauptmann

relevant) to the given event class, we formulate this task as a multi-instance learning (MIL) problem by taking each video as a bag and the video shots in each video as instances.

14 Event Detection

Simple to Complex Cross-modal Learning to Rank

no code implementations4 Feb 2017 Minnan Luo, Xiaojun Chang, Zhihui Li, Liqiang Nie, Alexander G. Hauptmann, Qinghua Zheng

The heterogeneity-gap between different modalities brings a significant challenge to multimedia information retrieval.

Cross-Modal Retrieval Information Retrieval +2

Uncovering Locally Discriminative Structure for Feature Analysis

no code implementations9 Jul 2016 Sen Wang, Feiping Nie, Xiaojun Chang, Xue Li, Quan Z. Sheng, Lina Yao

We propose a method that utilizes both the manifold structure of data and local discriminant information.

Strategies for Searching Video Content with Text Queries or Video Examples

no code implementations17 Jun 2016 Shoou-I Yu, Yi Yang, Zhongwen Xu, Shicheng Xu, Deyu Meng, Zexi Mao, Zhigang Ma, Ming Lin, Xuanchong Li, Huan Li, Zhenzhong Lan, Lu Jiang, Alexander G. Hauptmann, Chuang Gan, Xingzhong Du, Xiaojun Chang

The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search.

Event Detection Video Retrieval

Dynamic Concept Composition for Zero-Example Event Detection

no code implementations14 Jan 2016 Xiaojun Chang, Yi Yang, Guodong Long, Chengqi Zhang, Alexander G. Hauptmann

In this paper, we focus on automatically detecting events in unconstrained videos without the use of any visual training exemplars.

Event Detection Zero-Shot Learning

Unsupervised Feature Analysis with Class Margin Optimization

no code implementations3 Jun 2015 Sen Wang, Feiping Nie, Xiaojun Chang, Lina Yao, Xue Li, Quan Z. Sheng

In this paper, we propose an unsupervised feature selection method seeking a feature coefficient matrix to select the most distinctive features.

feature selection

Compound Rank-k Projections for Bilinear Analysis

no code implementations23 Nov 2014 Xiaojun Chang, Feiping Nie, Sen Wang, Yi Yang, Xiaofang Zhou, Chengqi Zhang

In many real-world applications, data are represented by matrices or high-order tensors.

Improved Spectral Clustering via Embedded Label Propagation

no code implementations23 Nov 2014 Xiaojun Chang, Feiping Nie, Yi Yang, Heng Huang

Our algorithm is built upon two advancements of the state of the art:1) label propagation, which propagates a node\'s labels to neighboring nodes according to their proximity; and 2) manifold learning, which has been widely used in its capacity to leverage the manifold structure of data points.

A Convex Formulation for Spectral Shrunk Clustering

no code implementations23 Nov 2014 Xiaojun Chang, Feiping Nie, Zhigang Ma, Yi Yang, Xiaofang Zhou

Thus, applying manifold information obtained from the original space to the clustering process in a low-dimensional subspace is prone to inferior performance.

Dimensionality Reduction

Balanced k-Means and Min-Cut Clustering

no code implementations23 Nov 2014 Xiaojun Chang, Feiping Nie, Zhigang Ma, Yi Yang

Clustering is an effective technique in data mining to generate groups that are the matter of interest.

A Convex Sparse PCA for Feature Analysis

no code implementations23 Nov 2014 Xiaojun Chang, Feiping Nie, Yi Yang, Heng Huang

In addition, based on the sparse model used in CSPCA, an optimal weight is assigned to each of the original feature, which in turn provides the output with good interpretability.

Dimensionality Reduction feature selection

Semi-supervised Feature Analysis by Mining Correlations among Multiple Tasks

no code implementations23 Nov 2014 Xiaojun Chang, Yi Yang

In this paper, we propose a novel semi-supervised feature selection framework by mining correlations among multiple tasks and apply it to different multimedia applications.

feature selection

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