Xin Jin 金鑫

I am an Assistant Professor at the College of Info Science & Technology, Eastern Institute for Advanced Study (EIAS) where I cooperated with professor Wenjun Zeng (IEEE Fellow). Our group is to engage in state of the art research in computer vision and deep learning.

Previously, I was a Visiting Scholar of Learning and Vision (LV) Lab at the National University of Singapore where I was guided by professor Xinchao Wang, professor Jiashi Feng and professor Shuicheng Yan. I received Ph.D. degree from University of Science and Technology of China (USTC), under the supervision of Zhibo Chen. From Jan. 2019 to Jul. 2020, I worked at Intelligent Multimedia Group (IMG) in MSRA under the supervision of Cuiling Lan. From Sep. 2018 to Jan. 2019, I worked at KDDI Research, Inc. in Japan under the supervision of Jianfeng Xu.

If you are highly creative, have top research/coding skill and interested in joining us, please do not hesitate to send me ( your CV and cc

Email:  /  Google Scholar  /  Github

profile photo

  • [07/2023] Four papers accepted by ICCV 2023~

  • [06/2023] One paper accepted by IEEE TIP~

  • [04/2023] Two papers accepted by IEEE TMM~

  • [04/2023] One paper accepted by ICML 2023~

  • [02/2023] Three papers accepted by CVPR 2023~

  • [09/2022] One paper accepted by NeurIPS 2022~

  • [07/2022] Two papers accepted by ECCV 2022~

  • [06/2022] One paper accepted by ACMMM 2022~

  • [03/2022] Three papers accepted by CVPR 2022~

  • [12/2021] Awarded the National Scholarship for Doctoral Students.

  • [12/2021] One paper accepted by IEEE TIP 2021.

  • [08/2021] One paper accepted by IEEE TMM 2021.

  • [07/2021] Two papers accepted by ICCV 2021 (one oral).

  • [12/2020] One paper accepted by AAAI 2021.

  • [07/2020] Two papers accepted by ECCV 2020.

  • [03/2020] Two papers accepted by CVPR 2020.

  • [11/2019] Three papers accepted by AAAI 2020.

  • Research

    I'm interested in image/video coding, person re-id, low-level vision and recently working on large model adaptation/generalization, prompt learning with CLIP model, etc.

    Discrete Point-wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face Recognition
    Qian Li*, Yuxiao Hu*, Ye Liu, Dongxiao Zhang, Xin Jin†, Yuntian Chen†
    CVPR, 2023  
    arxiv /

    In this work, by rethinking the inherent relationship between the face of target identity and its variants, we introduce a new pipeline of Generalized Manifold Adversarial Attack (GMAA) to achieve a better attack performance by expanding the attack range.

    Task Residual for Tuning Vision-Language Models
    Tao Yu*, Zhihe Lu*, Xin Jin, Zhibo Chen, Xinchao Wang
    CVPR, 2023  
    arxiv / code /

    In this work, we propose a new efficient tuning approach for VLMs named Task Residual Tuning (TaskRes), which performs directly on the text-based classifier and explicitly decouples the prior knowledge of the pre-trained models and new knowledge regarding a target task.

    Learning Distortion Invariant Representation for Image Restoration from A Causality Perspective
    Xin Li*, Bingchen Li*, Xin Jin, Cuiling Lan, Zhibo Chen
    CVPR, 2023  
    arxiv / code /

    In this work, we are the first to propose a novel training strategy for image restoration from the causality perspective, to improve the generalization ability of DNNs for unknown degradations.

    Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation
    Lin Chen*, Zhixiang Wei*, Xin Jin*(equal), Huaian Chen, Kai Chen, Yi Jin
    NeurIPS, 2022  
    arxiv / code /

    In this work, we resort to data mixing to establish a deliberated domain bridging (DDB) for domain adaptive semantic segmentation. The joint distributions of source and target domains are aligned and interacted with each other in the intermediate space.

    Image Coding for Machines with Omnipotent Feature Learning
    Ruoyu Feng*, Xin Jin*(equal), Zongyu Guo, Runsen Feng, Yixin Gao , Tianyu He , Zhizheng Zhang , Simeng Sun , Zhibo Chen
    ECCV, 2022  
    arxiv /

    In this paper, we attempt to learn a kind of omnipotent feature that is both general (for AI tasks) and compact (for compression) for Image Coding for Machines (ICM). Considering self-supervised learning (SSL) improves feature generalization, we integrate it with the compression task to learn such features.

    Learning with Recoverable Forgetting
    Jingwen Ye, Yifang Fu, Jie Song, Xingyi Yang, Songhua Liu, Xin Jin, Mingli Song, Xinchao Wang
    ECCV, 2022  
    arxiv /

    In this paper, we explore a novel learning scheme, termed as Learning wIth Recoverable Forgetting (LIRF), that explicitly handles the task- or sample-specific knowledge removal and recovery.

    Meta Clustering Learning for Large-scale Unsupervised Person Re-identification
    Xin Jin, Tianyu He, Xu Shen, Tongliang Liu, Xinchao Wang , Jianqiang Huang , Zhibo Chen, Xian-Sheng Hua
    ACMMM, 2022  
    arxiv /

    In this paper, we make attempt to the large-scale Unsupervised ReID and propose a “small data for big task” paradigm dubbed Meta Clustering Learning (MCL), which our method significantly saves computational cost while achieving a comparable or even better performance compared to prior works.

    Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification
    Zizheng Yang, Xin Jin, Kecheng Zheng, Feng Zhao
    CVPR, 2022  
    arxiv / code /

    We design an Unsupervised Pre-training framework for ReID based on the contrastive learning (CL) pipeline, dubbed UP-ReID.

    Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization
    Xin Jin, Tianyu He, Kecheng Zheng, Zhiheng Ying, Xu Shen, Zhen Huang , Ruoyu Feng , Jianqiang Huang , Xian-Sheng Hua , Zhibo Chen
    CVPR, 2022  
    arxiv / code /

    We focus on handling well the Cloth-Changing ReID problem under a more challenging setting, i.e., just from a single image, which enables high-efficiency and latency-free pedestrian identify for real-time surveillance applications.

    Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation
    Lin Chen, Huaian Chen, Zhixiang Wei, Xin Jin, Xiao Tan, Yi Jin, Enhong Chen
    CVPR, 2022  
    arxiv / code /

    We address the adversarial-based DA problem from a different perspective and design a simple yet effective adversarial paradigm in the form of a discriminator-free adversarial learning network (DALN), wherein the category classifier is reused as a discriminator.

    Dual Prior Learning for Blind and Blended Image Restoration
    Xin Jin, Li Zhang, Chaowei Shan, Xin Li, Zhibo Chen
    IEEE TIP, 2021  
    paper /

    We propose the Dual Prior Learning (DPL) method for blind image restoration by taking both image and distortion priors into account. DPL goes beyond DIP (deep image prior) by considering an additional step to explicitly learn the blended distortion prior.

    Style Normalization and Restitution for DomainGeneralization and Adaptation
    Xin Jin, Cuiling Lan, Wenjun Zeng, Zhibo Chen
    IEEE TMM, 2021  
    paper / code /

    We design a novel Style Normalization and Restitution module (SNR) to simultaneously ensure both high generalization and discrimination capability of the networks, and evaluate it on multiple vision tasks of classification, detection, segmentation, etc.

    Re-energizing Domain Discriminator with Sample Relabeling for Adversarial Domain Adaptation
    Xin Jin, Cuiling Lan, Wenjun Zeng, Zhibo Chen
    ICCV, 2021  
    paper /

    We propose an efficient optimization strategy named Re-enforceable Adversarial Domain Adaptation (RADA) which aims to re-energize the domain discriminator during the training by using dynamic domain labels.

    Dense Interaction Learning for Video-based Person Re-identification
    Tianyu He, Xin Jin, Xu Shen, Jianqiang Huang, Zhibo Chen, Xian-Sheng Hua
    ICCV, 2021 (Oral)  
    paper /

    This paper proposes a hybrid framework, Dense Interaction Learning (DenseIL), that takes the principal advantages of both CNN-based and Attention-based architectures to tackle video-based person re-ID difficulties.

    Learning Omni-frequency Region-adaptive Representations for Real Image Super-Resolution
    Xin Li*, Xin Jin*, Tao Yu, Yingxue Pang, Simeng Sun, Zhizheng Zhang, Zhibo Chen
    *Equal Contribution AAAI, 2021  
    arxiv /

    The key to solving this more challenging real image super-resolution (RealSR) problem lies in learning feature representations that are both informative and content-aware. We propose an Omni-frequency Region-adaptive Network (OR-Net), here we call features of all low, middle and high frequencies omni-frequency features.

    Global Distance-distributions Separation for Unsupervised Person Re-identification
    Xin Jin, Jiawei Liu, Cuiling Lan, Wenjun Zeng, Zhibo Chen
    ECCV, 2020  
    paper /

    We introduce a global distance-distributions separation (GDS) constraint over the two distributions to encourage the clear separation of positive and negative samples from a global view.

    Learning Disentangled Feature Representation for Hybrid-distorted Image Restoration
    Xin Li , Xin Jin, Jianxin Lin, Tao Yu, Sen Liu , Yaojun Wu , Wei Zhou, Zhibo Chen
    ECCV, 2020  
    paper /

    We introduce the concept of Disentangled Feature Learning to achieve the feature-level divide-and-conquer of hybrid distortions for low-level enhancement.

    Style normalization and restitution for generalizable person re-identification
    Xin Jin, Cuiling Lan, Wenjun Zeng, Zhibo Chen, Li Zhang
    CVPR, 2020  
    paper / code /

    We propose a simple yet effective Style Normalization and Restitution (SNR) module. Specifically, we filter out style variations (eg, illumination, color contrast) by Instance Normalization (IN). However, such a process inevitably removes discriminative information. We propose to distill identity-relevant feature from the removed information and restitute it to the network to ensure high discrimination.

    Relation-Aware Global Attention
    Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Xin Jin, Zhibo Chen

    CVPR, 2020  
    paper / code /

    We propose an effective Relation-Aware Global Attention (RGA) module which captures the global structural information for better attention learning.

    Semantics-aligned representation learning for person re-identification
    Xin Jin, Cuiling Lan, Wenjun Zeng, Guoqiang Wei, Zhibo Chen
    AAAI, 2020  
    paper / code /

    We build a Semantics Aligning Network (SAN) which consists of a base network as encoder (SA-Enc) for re-ID, and a decoder (SA-Dec) for reconstructing the densely semantics aligned full texture image.

    Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification
    Xin Jin, Cuiling Lan, Wenjun Zeng, Zhibo Chen
    AAAI, 2020  
    paper /

    We propose exploiting the multi-shots of the same identity to guide the feature learning of each individual image. Specifically, we design an Uncertainty-aware Multi-shot Teacher-Student (UMTS) Network.

    Region Normalization for Image Inpainting
    Tao Yu, Zongyu Guo, Xin Jin, Shilin Wu, Zhibo Chen, Weiping Li, Zhizheng Zhang, Sen Liu

    AAAI, 2020  
    paper / code

    We show that the mean and variance shifts caused by full-spatial FN limit the image inpainting network training and we propose a spatial region-wise normalization named Region Normalization (RN) to overcome the limitation.

    Academic Services
    Invited Reviewer for IEEE TIP, IEEE TNNLS, IEEE TIP, IEEE TCSVT, Pattern Recognition

    Invited Reviewer for NeurIPS-2022, ECCV-2022, ACMMM-2022, CVPR-2022, AAAI-2022 (PC), ICCV-2021, CVPR-2021, AAAI-2021, ACMMM-2020, VCIP-2020, etc.

    Feel free to steal this website's source code.