Lei's Homepage

News

[2026.05]
招收2027级保研的同学。要求：1）较好的代码能力；2）较好的自我驱动能力；3）具有人工智能领域科研基础。
PS: 如果我觉得符合基本要求，会在三日内回复邮件。
[2020.10] My homepage is launched.

About Me

I am an Associate Professor in the School of Computer Science and Engineering at Southeast University. I was a Zhishan Postdoctoral Researcher working with Prof. Xin Geng at Southeast University. I got my Ph. D. degree from Nanjing University in 2020, supervised by Prof. Yang Gao. In 2011 and 2015, I obtained my bachelor degree and master degree (supervised by Prof. Mingwu Ren) from Nanjing Normal University and Nanjing University of Science and Technology. From August 2018 to August 2019, I was a visiting student at University of Wollongong, supervised by Prof. Lei Wang.

Research Interests

My research interests include Computer Vision (CV) and Pattern Recogintion (PR).

Currently, I mainly focus on the CV topics including Person Re-identification, Anomaly Detection and Semantic Segmentation, etc.
For PR, I am interested in Domain Generalization (DG) and Vision-Language Model (VLM).

Selected Publications

*: Equal Contribution; : Corresponding Author.

Xin Huang, Long Chen, Qian Yu, Lei Qi. GTR: Global Token Retrieval for Window-Based Vision Transformer. IEEE Transactions on Cognitive and Developmental Systems (IEEE TCDS), 2026. [IEEE汇刊] 第一作者为指导的硕士生
Lei Qi, Zeyu Shi, Peng Dong, Xin Geng. Explore Diverse Information in Diffusion Model for Single-domain Generalized Object Detection. Pattern Recognition (PR), 2026. [CCF-B期刊/模式识别领域旗舰期刊]
Longhua Li, Lei Qi, Qi Tian, Xin Geng. Model Merging in the Essential Subspace. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026. [CCF-A会议/CV顶会] 第一作者为联合指导的博士生
Xin Huang, Longhua Li, Lei Qi, Xin Geng. Few-Shot Network Thinning: A Unified Dense Compression Framework for CNNs and ViTs. IEEE Transactions on Mobile Computing (IEEE TMC), 2026. [CCF-A期刊/IEEE汇刊] 第一作者为指导的硕士生
Longhua Li, Lei Qi, Xin Geng. Stratified Knowledge-Density Super-Network for Scalable Vision Transformers. AAAI Conference on Artificial Intelligence (AAAI), 2026. [CCF-A会议] 第一作者为联合指导的博士生
Longhua Li, Lei Qi, Xin Geng. One-Shot Knowledge Transfer for Scalable Person Re-Identification. IEEE International Conference on Computer Vision (ICCV), 2025. [CCF-A会议/CV顶会] 第一作者为联合指导的博士生
Xingyu Zhao, Lei Qi, Yuexuan An, Xin Geng. Delving into Generalizable Label Distribution Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2025. [CCF-A期刊/IEEE汇刊] 第一作者为联合指导的博士生
Huazhong Zhao, Lei Qi, Xin Geng. CILP-FGDI: Exploiting Vision-Language Model for Generalizable Person Re-Identification. IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2025. [CCF-A期刊/IEEE汇刊] 第一作者为指导的硕士生
Xiusheng Xu, Lei Qi, Jingyang Zhou, Xin Geng. BatStyler: Advancing Multi-category Style Generation for Source-free Domain Generalization. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2025. [CCF-B期刊/IEEE汇刊] 第一作者为指导的硕士生
Chenghao Li, Lei Qi, Xin Geng. A SAM-guided Two-stream Lightweight Model for Anomaly Detection. ACM Transactions on Multimedia Computing Communications and Application (ACM TOMM), 2024. [CCF-B期刊/ACM汇刊] 第一作者为指导的硕士生
Huazhong Zhao, Lei Qi, Xin Geng. CLIP-DFGS: A Hard Sample Mining Method for CLIP in Generalizable Person Re-Identification. ACM Transactions on Multimedia Computing Communications and Application (ACM TOMM), 2024. [CCF-B期刊/ACM汇刊] 第一作者为指导的硕士生
Jintao Guo, Lei Qi, Yinghuan Shi, Yang Gao. START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation. Advances in Neural Information Processing Systems (NeurIPS), 2024. [CCF-A会议/ML顶会] 第一作者为联合指导的博士生
Xingyu Zhao, Yuexuan An, Lei Qi, Xin Geng. Scalable Label Distribution Learning for Multi-Label Classification. IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS), 2024. [CCF-B期刊/IEEE汇刊] 第一作者为联合指导的博士生
Lei Qi, Dongjia Zhao, Yinghuan Shi, Xin Geng. Patch-aware Batch Normalization for Improving Cross-domain Robustness. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2024. [CCF-B期刊/IEEE汇刊]
Yunlong Tang, Yuxuan Wan, Lei Qi, Xin Geng. DPStyler: Dynamic PromptStyler for Source-Free Domain Generalization. IEEE Transactions on Multimedia (IEEE TMM), 2024. [CCF-B期刊/IEEE汇刊] 第一作者为联合指导的硕士生
Dongjia Zhao, Lei Qi, Xiao Shi, Yinghuan Shi, Xin Geng. A Novel Cross-Perturbation for Single Domain Generalization. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2024. [CCF-B期刊/IEEE汇刊] 第一作者为指导的硕士生
Jiajun Hu, Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao. Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization. European Conference on Computer Vision (ECCV), 2024. [CCF-B会议/CV顶会] 第一作者为联合指导的硕士生
Lei Qi, Ziang Liu, Yinghuan Shi, Xin Geng. Generalizable Metric Network for Cross-domain Person Re-identification. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2024. [CCF-B期刊/IEEE汇刊]
Lei Qi, Hongpeng Yang, Yinghuan Shi, Xin Geng. MultiMatch: Multi-task Learning for Semi-supervised Domain Generalization. ACM Transactions on Multimedia Computing Communications and Application (ACM TOMM), 2024. [CCF-B期刊/ACM汇刊]
Lei Qi, Hongpeng Yang, Yinghuan Shi, Xin Geng. NormAUG: Normalization-guided Augmentation for Domain Generalization. IEEE Transactions on Image Processing (IEEE TIP), 2024. [CCF-A期刊/IEEE汇刊]
Na Wang^*, Lei Qi^*, Jintao Guo, Yinghuan Shi, Yang Gao. Learning Generalizable Models via Disentangling Spurious and Enhancing Potential Correlations. IEEE Transactions on Image Processing (IEEE TIP), 2023. [CCF-B期刊/IEEE汇刊] 第一作者为联合指导的硕士生
Lei Qi, Zihao Ren, Junxi Liu, Xin Geng. Person Re-identification Method Based on Hybrid Real-Synthetic Data. Journal of Computer Research and Development (计算机研究与发展), 2023. [CCF-T1期刊]
Lei Qi, Peng Dong, Tan Xiong, Hui Xue, Xin Geng. DoubleAUG: Single-domain Generalized Object Detector in Urban via Color Perturbation and Dual-style Memory. ACM Transactions on Multimedia Computing Communications and Application (ACM TOMM), 2023. [CCF-B期刊/ACM汇刊]
Xingyu Zhao, Lei Qi, Yuexuan An, Xin Geng. Generalizable Label Distribution Learning. ACM International Conference on Multimedia (MM), 2023. [CCF-A会议] 第一作者为联合指导的博士生
Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao. DomainAdaptor: A Novel Approach to Test-time Adaptation. IEEE International Conference on Computer Vision (ICCV), 2023. [CCF-A会议/CV顶会] 第一作者为联合指导的博士生
Jintao Guo, Lei Qi, Yinghuan Shi. DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization. IEEE International Conference on Computer Vision (ICCV), 2023. [CCF-A会议/CV顶会] 第一作者为联合指导的博士生
Jiajun Hu^*, Lei Qi^*, Jian Zhang, Yinghuan Shi. Domain generalization via Inter-domain Alignment and Intra-domain Expansion. Pattern Recognition (PR), 2023. [CCF-B期刊/模式识别领域旗舰期刊] 第一作者为联合指导的硕士生
Jintao Guo, Lei Qi, Yinghuan Shi, Yang Gao. PLACE dropout: A Progressive Layer-wise and Channel-wise Dropout for Domain Generalization. ACM Transactions on Multimedia Computing Communications and Application (ACM TOMM), 2023. [CCF-B期刊/ACM汇刊] 第一作者为联合指导的博士生
Lei Qi, Jiaqi Liu, Lei Wang, Yinghuan Shi, Xin Geng. Unsupervised Generalizable Multi-source Person Re-identification: A Domain-specific Adaptive Framework. Pattern Recognition (PR), 2023. [CCF-B期刊/模式识别领域旗舰期刊]
Jintao Guo, Na Wang, Lei Qi, Yinghuan Shi. ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-Frequency Transform for Domain Generalization. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [CCF-A会议/CV顶会] 第一作者为联合指导的博士生
Lihe Yang, Lei Qi, Litong Feng, Wayne Zhang, Yinghuan Shi. Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [CCF-A会议/CV顶会] 第一作者为联合指导的硕士生
Lei Qi, Jiaying Shen, Jiaqi Liu, Yinghuan Shi, Xin Geng. Label Distribution Learning for Generalizable Multi-source Person Re-identification. IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2022. [CCF-A期刊/IEEE汇刊]
Ruiqi Wang^*, Lei Qi^*, Yinghuan Shi, Yang Gao. Better Pseudo-label: Joint Domain-aware Label and Dual-classifier for Semi-supervised Domain Generalization. Pattern Recognition (PR), 2022. [CCF-B期刊/模式识别领域旗舰期刊] 第一作者为联合指导的硕士生
Lei Qi, Lei Wang, Yinghuan Shi, Xin Geng. A Novel Mix-normalization Method for Generalizable Multi-source Person Re-identification. IEEE Transactions on Multimedia (IEEE TMM), 2022. [CCF-B期刊/IEEE汇刊]
Yue Wang^*, Lei Qi^*, Yinghuan Shi, Yang Gao. Feature-based Style Randomization for Domain Generalization. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2022. [CCF-B期刊/IEEE汇刊] 第一作者为联合指导的硕士生
Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao. MVDG: A Unified Multi-view Framework for Domain Generalization. European Conference on Computer Vision (ECCV), 2022. [CCF-B会议/CV顶会] 第一作者为联合指导的博士生
Ziqi Zhou, Lei Qi, Yinghuan Shi. Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image Restoration. European Conference on Computer Vision (ECCV), 2022. [CCF-B会议/CV顶会] 第一作者为联合指导的硕士生
Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao. Generalizable Model-agnostic Semantic Segmentation via Target-specific Normalization. Pattern Recognition (PR), 2021. [CCF-B期刊/模式识别领域旗舰期刊] 第一作者为联合指导的博士生
Xiaoting Han^*, Lei Qi^*, Qian Yu, Ziqi Zhou, Yefeng Zheng, Yinghuan Shi, Yang Gao. Deep Symmetric Adaptation Network for Cross-modality Medical Image Segmentation. IEEE Transactions on Medical Imaging (IEEE TMI), 2021. [CCF-B期刊/IEEE汇刊] 第一作者为联合指导的硕士生
Lei Qi, Lei Wang, Jing Huo, Yinghuan Shi, Xin Geng, Yang Gao. Adversarial Camera Alignment Network for Unsupervised Cross-camera Person Re-identification. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2021. [CCF-B期刊/IEEE汇刊]
Lei Qi, Lei Wang, Jing Huo, Yinghuan Shi, Yang Gao. GreyReID: A Two-stream Deep Framework with RGB-grey Information for Person Re-identification. ACM Transactions on Multimedia Computing Communications and Application (ACM TOMM), 2020. [CCF-B期刊/ACM汇刊]
Lei Qi, Peize Yu, Yang Gao. Research on Weak-Supervised Person Re-Identification. Journal of Software (软件学报), 2020. [CCF-T1期刊]
Lei Qi, Lei Wang, Jing Huo, Yinghuan Shi, Yang Gao. Progressive Cross-camera Soft-label Learning for Semi-supervised Person Re-identification. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2020. [CCF-B期刊/IEEE汇刊]
Lei Qi, Lei Wang, Jing Huo, Luping Zhou, Yinghuan Shi, Yang Gao. A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification. IEEE International Conference on Computer Vision (ICCV), 2019. [CCF-A会议/CV顶会]

Teaching

Artificial Intelligence (人工智能) - Fall 2025

毕业生去向

东南大学硕士毕业生（包括联合指导的学生）

2025 ：董鹏（理想汽车）、赵烨程（选调）、赵懂佳（小红书，国奖）、赵华众（电信，国奖）、李成浩（电网）、唐云龙（字节）、徐义格（美团）
2024 ：万宇轩（北大读博）、刘家奇（寒武纪）、疏越（西艾爱）、高明（定向）、阳鸿鹏（电网）、刘子昂（农业银行）
2023 ：沈珈莹（公务员，国奖）、刘俊汐（微软）、熊坦（选调）、梅涛（华为）
2022 ：宋馨雅（华为）、刘茂林（商汤）、付坤（定向）