1 code implementation • 16 Jan 2023 • Xiaotong Li, Zixuan Hu, Jun Liu, Yixiao Ge, Yongxing Dai, Ling-Yu Duan
In this paper, we improve the network generalization ability by modeling domain shifts with uncertainty (DSU), i. e., characterizing the feature statistics as uncertain distributions during training.
1 code implementation • 3 Mar 2022 • Yongxing Dai, Yifan Sun, Jun Liu, Zekun Tong, Yi Yang, Ling-Yu Duan
Instead of directly aligning the source and target domains against each other, we propose to align the source and target domains against their intermediate domains for a smooth knowledge transfer.
1 code implementation • ICLR 2022 • Xiaotong Li, Yongxing Dai, Yixiao Ge, Jun Liu, Ying Shan, Ling-Yu Duan
In this paper, we improve the network generalization ability by modeling the uncertainty of domain shifts with synthesized feature statistics during training.
1 code implementation • NeurIPS 2021 • Zekun Tong, Yuxuan Liang, Henghui Ding, Yongxing Dai, Xinke Li, Changhu Wang
However, it is still in its infancy with two concerns: 1) changing the graph structure through data augmentation to generate contrastive views may mislead the message passing scheme, as such graph changing action deprives the intrinsic graph structural information, especially the directional structure in directed graphs; 2) since GCL usually uses predefined contrastive views with hand-picking parameters, it does not take full advantage of the contrastive information provided by data augmentation, resulting in incomplete structure information for models learning.
3 code implementations • ICCV 2021 • Yongxing Dai, Jun Liu, Yifan Sun, Zekun Tong, Chi Zhang, Ling-Yu Duan
To ensure these two properties to better characterize appropriate intermediate domains, we enforce the bridge losses on intermediate domains' prediction space and feature space, and enforce a diversity loss on the two domain factors.
Domain Adaptive Person Re-Identification Person Re-Identification
no code implementations • CVPR 2021 • Yongxing Dai, Xiaotong Li, Jun Liu, Zekun Tong, Ling-Yu Duan
Specifically, we propose a decorrelation loss to make the source domain networks (experts) keep the diversity and discriminability of individual domains' characteristics.
1 code implementation • 26 Dec 2020 • Yongxing Dai, Jun Liu, Yan Bai, Zekun Tong, Ling-Yu Duan
To this end, we propose a novel approach, called Dual-Refinement, that jointly refines 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.