|
I am a fourth year Ph.D student at the National Engineering Research Center of Visual Technology (NELVT), School of Computer Science, Peking University, supervised by Prof. Ling-Yu Duan. In 2018, I obtained my B.Eng. degree in computer science and technology from Xidian University, Xi’an, China. My current research focuses on computer vision and trasnfer learning, especially person re-identification, domain adaptation, and domain generalization. |
|
|
2022-03: Invitated as a reviewer for NeurIPS 2022. 2022-01: One paper is accepted by ICLR 2022. 2021-09: One paper is accepted by NeurIPS 2021. 2021-07: One paper is accepted by ICCV 2021 and one paper is accepted by TIP. |
|
|
|
Yongxing Dai, Yifan Sun, Jun Liu, Zekun Tong, Yi Yang, Ling-Yu Duan Arxiv preprint, 2022 paper / code / bibtex IDM++ is a journal extension of IDM (ICCV 2021 Oral). We further propose a Mirrors Generation Module (MGM) to reinforce IDM into IDM++. IDM++ provides a unified framework for two popular cross-domain re-ID scenarios (i.e., UDA and DG). Twelve UDA re-ID benchmarks and two DG re-ID protocols validate that IDM++ brings general improvement and sets new state of the art for both scenarios. |
|
Xiaotong Li, Yongxing Dai, Yixiao Ge, Jun Liu, Ying Shan, Ling-Yu Duan ICLR, 2022 paper / code / bibtex We improve the network generalization ability by modeling the uncertainty of domain shifts with synthesized feature statistics during training. Our method shows its superiority on a wide range of out-of-distribution (OOD) vision tasks including image classification, semantic segmentation, and instance retrieval. |
|
Zekun Tong, Yuxuan Liang, Henghui Ding, Yongxing Dai, Xinke Li, Changhu Wang, NeurIPS, 2021 paper / code / bibtex We design a digraph data augmentation method called Laplacian perturbation and theoretically analyze how it provides contrastive information without changing the digraph structure. |
|
Yongxing Dai, Jun Liu, Yifan Sun, Zekun Tong, Chi Zhang, Ling-Yu Duan ICCV, 2021 (Oral Presentation) paper / arXiv / code / bibtex IDM is a plug-and-play module to generate intermediate domains' representations, which can bridge source and target domains in unsupervised domain adaptive person re-ID. |
|
Yongxing Dai, Jun Liu, Yan Bai, Zekun Tong, Ling-Yu Duan IEEE Transactions on Image Processing (TIP), 2021 paper / arXiv / code / bibtex Dual-Refinement can jointly refine pseudo labels at the off-line clustering phase and features at the on-line training phase, to alternatively boost the label purity and feature discriminability in the target domain for more reliable re-ID. |
|
Yongxing Dai, Xiaotong Li, Jun Liu, Zekun Tong, Ling-Yu Duan CVPR, 2021 paper / arXiv / bibtex We propose a novel method called the relevance-aware mixture of experts (RaMoE), using an effective voting-based mixture mechanism to dynamically leverage source domains’ diverse characteristics to improve the model’s generalization |
|
Yan Bai, Yihang Lou, Yongxing Dai, Jun Liu, Ziqian Chen, Ling-Yu Duan IJCAI, 2020 paper / bibtex We propose a Disentangled Feature Learning Network (DFLNet) to learn orientation specific and common features concurrently. Moreover, to effectively use these two types of features for ReID, we further design a feature metric alignment scheme to ensure the consistency of the metric scales. |
|
NELVT Outstanding Student 2021 Peking University President Scholarship 2021-2022 Lee Wai Wing Scholarship 2020-2021 Merit Student of Peking University 2021 |
|
Journal Reviewer:TIP, TMM, Neurocomputing Conference Reviewer:NeurIPS 2022, ICLR 2022 |
|
|