I am a four-year Ph.D. student and luckily advised by Prof. Cairong Zhao. I am passionate about computer vision research in the following topics:

  1. Human-centric Video Understanding: Trustworthy Person Re-identification-Robust, Security, and Privacy-Preserving
  2. MSRA Research Intern Directions: Infographic understanding & NAS benchmark

Currently, I base my research topics on emerging abilities in foundation models such as LVM for ReID and LLM for VIS. I am always grateful to those more senior who have a deep understanding of these topics for their advice. Besides, I am always willing to collaborate with people interested in relevant issues and provide corresponding guidance to younger students (undergrad or master).

CV

You can download my CV at here.

I am actively seeking a Research Scientist or Postdoc Research Fellow. Please feel free to reach out if you have any suitable positions!

News

Sep 26, 2024 : A paper on ‘Fetch and Forge:Efficient Dataset Condensation for Object Detection’ is accepted by the NeurIPS 2024 (CCF A).

Aug 13, 2024 : I have been invited to be a Reviewer for the International Conference on Learning Representations (ICLR) 2025 Conference.

July 19, 2024 : I have been invited to be a Program Committee for AAAI 2025.

May 08, 2024 : I have been invited to be a Reviewer for the NeurIPS 2024 Conference.

May 04, 2024 : A paper on ‘ReID-Leak:Membership Inference Attacks Against Person Re-identification’ is accepted by the International Journal of Computer Vision in 2024 (CCF A).

April 23, 2024 : A paper on ‘Reviving Static Charts into Live Charts’ is accepted by IEEE Transactions on Visualization and Computer Graphics T-VCG in 2024 (CCF A).

April 21, 2024 : A paper on ‘Hierarchically Recognizing Vector Graphics and A New Chart-based Vector Graphics Dataset’ is accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence in 2024 (CCF A).

April 13, 2024 : A paper on ‘Adaptive Discriminative Regularization for Visual Classification’ is accepted by the International Journal of Computer Vision in 2024 (CCF A).

see all news

doushuguang52@163.com
Google Scholar IEEE Student Member
SH021, Shanghai, China.

Publications

Fetch and Forge:Efficient Dataset Condensation for Object Detection

Current research on DC mainly focuses on image classification, with less exploration of object detection. As a remedy, we propose DCOD, the first dataset condensation framework for object detection. It initially storing key localization and classification information into model parameters, and then reconstructing synthetic images via model inversion.

Ding Qi, Jian Li, Jinlong Peng, Shuguang Dou, Jialin Li, Bo Zhao, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Cairong Zhao

Neural Information Processing Systems (CCF A)

pdf / project page / code (GitHub) / Website Online

Re-ID-leak:Membership Inference Attacks Against Person Re-identification

Most existing MI attack methods focus on classification models, while Re-ID follows a distinct paradigm for training and inference. Re-ID is a fine-grained recognition task that involves complex feature embedding, and the model outputs commonly used by existing MI algorithms, such as logits and losses, are inaccessible during inference. We propose a novel MI attack method based on the distribution of inter-sample similarity, which involves sampling a set of anchor images to represent the similarity distribution that is conditioned on a target image.

Junyao Gao, Xinyang Jiang, Shuguang Dou, Dongsheng Li, Duoqian Miao, Cairong Zhao

International Journal of Computer Vision 2024 (CCF A)

pdf / project page / code (GitHub) / Website Online

Reviving static charts into live charts

Data charts are prevalent across various fields due to their efficacy in conveying complex data relationships. However, static charts may sometimes struggle to engage readers and efficiently present intricate information, potentially resulting in limited understanding. We introduce “Live Charts,” a new format of presentation that decomposes complex information within a chart and explains the information pieces sequentially through rich animations and accompanying audio narration.

Lu Ying, Yun Wang, Haotian Li, Shuguang Dou, Haidong Zhang, Xinyang Jiang, Huamin Qu, Yingcai Wu

IEEE Transactions on Visualization and Computer Graphics (CCF A)

pdf / project page / code (GitHub) / Website Online

Hierarchically Recognizing Vector Graphics and A New Chart-based Vector Graphics Dataset

The conventional approach to image recognition has been based on raster graphics, which can suffer from aliasing and information loss when scaled up or down. In this paper, we propose a novel approach that leverages the benefits of vector graphics for object localization and classification. Our method, called YOLaT (You Only Look at Text), takes the textual document of vector graphics as input, rather than rendering it into pixels. We propose YOLaT++ to learn Multi-level Abstraction Feature Learning from Primitive Shapes to Curves and Points. On the other hand, given few public datasets focus on vector graphics, data-driven learning cannot exert its full power on this format. We provide a large-scale and challenging dataset for Chart-based Vector Graphics Detection and Chart Understanding, termed VG-DCU, with vector graphics, raster graphics, annotations, and raw data drawn for creating these vector charts.

Shuguang Dou, Xinyang Jiang, Lu Liu, Lu Ying, Caihua Shan, Yifei Shen, Xuanyi Dong, Yun Wang, Dongsheng Li, Cairong Zhao

IEEE T-PAMI 2024 (CCF A)

pdf / project page / code (GitHub) / Website Online

Adaptive Discriminative Regularization for Visual Classification

How to improve discriminative feature learning is central in classification. In this paper, we embrace the real-world data distribution setting in that some classes share semantic overlaps due to their similar appearances or concepts. Regarding this hypothesis, we propose a novel regularization to improve discriminative learning. We first calibrate the estimated highest likelihood of one sample based on its semantically neighboring classes, then encourage the overall likelihood predictions to be deterministic by imposing an adaptive exponential penalty.

Qingsong Zhao, Yi Wang, Shuguang Dou, Chen Gong, Yin Wang and Cairong Zhao

International Journal of Computer Vision 2024 (CCF A)

pdf / project page / code (GitHub) / Website Online

Invisible backdoor attack with dynamic triggers against person re-identification

Existing backdoor attack methods follow an all-to-one or all-to-all attack scenario, where all the target classes in the test set have already been seen in the training set. However, ReID is a much more complex fine-grained open-set recognition problem, where the identities in the test set are not contained in the training set. To ameliorate this issue, we propose a novel backdoor attack on deep ReID under a new all-to-unknown scenario, called Dynamic Triggers Invisible Backdoor Attack (DT-IBA). Instead of learning fixed triggers for the target classes from the training set, DT-IBA can dynamically generate new triggers for any unknown identities.

Wenli Sun, Xinyang Jiang, Shuguang Dou, Dongsheng Li, Duoqian Miao, Cheng Deng, Cairong Zhao

IEEE T-IFS 2023 (CCF A)

pdf / project page / code (GitHub) / Website Online

EA-HAS-Bench:Energy-Aware Hyperparameter and Architecture Search Benchmark

We present the first large-scale energy-aware benchmark that allows studying AutoML methods to achieve better trade-offs between performance and search energy consumption, named EA-HAS-Bench. EA-HAS-Bench provides a large-scale architecture/hyperparameter joint search space, covering diversified configurations related to energy consumption.

Shuguang Dou, Xinyang Jiang, Cairong Zhao, Dongsheng Li

ICLR 2023 Spotlight

pdf / project page / code (GitHub) / Website Online

Human Co-Parsing Guided Alignment for Occluded Person Re-identification

We propose a novel Human Co-parsing Guided Alignment (HCGA) framework that alternately trains the human co-parsing network and the ReID network, where the human co-paring network is trained in a weakly supervised manner to obtain paring results without any extra annotation.

Shuguang Dou, Cairong Zhao, Xinyang Jiang, Shanshan Zhang, Member, IEEE, Wei-Shi Zheng, Wangmeng Zuo, Senior Member, IEEE

IEEE T-IP 2022 (CCF A)

pdf / project page / code (GitHub) / Website Online

Detecting Overlapped Objects in X-ray Security Imagery by a Label-aware Mechanism

One of the key challenges to the X-ray security checkis to detect the overlapped items in backpacks or suitcases in the X-ray images. Most existing methods improve the robustness of models to the object overlapping problem by enhancing the underlying visual information such as colors and edges. However, this strategy ignores the situations in that the objects have similar visual clues as to the background, and objects overlapping each other. Since the two cases rarely appear in existing datasets, we contribute a novel dataset – Cutters and Liquid Containers X-ray Dataset (CLCXray) to complete the related research.

Cairong Zhao*, Liang Zhu*, Shuguang Dou, Weihong Deng, and Liang Wang, Fellow, IEEE (*Co-First Authors)

IEEE T-IFS 2022 (CCF A)

pdf / project page / code (GitHub) / Website Online

Incremental Generative Occlusion Adversarial Suppression Network for Person ReID

To address the occlusion problem, we propose a novel Incremental Generative Occlusion Adversarial Suppression (IGOAS) network.

Cairong Zhao*, Xinbi Lv*, Shuguang Dou*, Shanshan Zhang, Member, IEEE, Jun Wu, Senior Member, IEEE, and Liang Wang, Fellow, IEEE (*Co-First Authors)

IEEE T-IP 2021 (CCF A)

pdf / project page / code (GitHub) / Website Online

Alternately Updated Spectral–Spatial Convolution Network for the Classification of Hyperspectral Images

The connection structure in the convolutional layers of most deep learning-based algorithms used for the classification of hyperspectral images (HSIs) has typically been in the forward direction. In this study, an end-to-end alternately updated spectral–spatial convolutional network (AUSSC) with a recurrent feedback structure is used to learn refined spectral and spatial features for HSI classification.

Wenju Wang, Shuguang Dou^, Sen Wang (^Corresponding Author and First Student Author)

Remote sensing 2019

pdf / project page / code (GitHub) / Website Online

A fast dense spectral-spatial convolutional network framework for hyperspectral image classification

To reduce the training time and improve accuracy, in this paper we propose an end-to-end fast dense spectral–spatial convolution (FDSSC) framework for HSI classification.

Wenju Wang, Shuguang Dou^, Zhongmin Jiang and Liujie Sun (^Corresponding Author and First Student Author)

Remote sensing 2018(ESI Highly Cited PaperCitation 300+

pdf / project page / code (GitHub) / Website Online


see all publications

Friends

YuanPeng Tu (https://yuanpengtu.github.io/) : The most abstract man in ViLL Lab.

Shuyang Feng : The most thoughtful man in ViLL Lab.

Qingsong Zhao (https://zqsiat.github.io/) : A stubborn person who knows his path.

Junyao Gao (https://jeoyal.github.io/home/) : A sincere person in Vill Lab.

Yubin Wang (https://thomaswangy.github.io/) : The most trustworthy person in Vill lab.

Wenli Sun : My makeup artist in Vill lab.

Yan Li : Colleague in the MSRA and MSRA first Winners and Hard Worker.

Longtao Tang : Colleague in the MSRA and the man I admire most in the MSRA.

see all friends

Theses

Research on Feature Learning and Application of Three-dimensional Point Cloud

Learning deep features from 3D point cloud for classification and retrieval. This work will be done before 12/2019.

Shuguang Dou

Master Thesis, College of Communication and Art Design, University of Shanghai for Science and Technology; December, 2019

pdf in Chinese (Temporarily unavailable)