1 code implementation • 16 Oct 2023 • Yiyuan Zhang, Kaixiong Gong, Xiaohan Ding, Kaipeng Zhang, Fangrui Lv, Kurt Keutzer, Xiangyu Yue
We propose $\textbf{UniDG}$, a novel and $\textbf{Uni}$fied framework for $\textbf{D}$omain $\textbf{G}$eneralization that is capable of significantly enhancing the out-of-distribution generalization performance of foundation models regardless of their architectures.
Ranked #1 on Domain Generalization on TerraIncognita
1 code implementation • CVPR 2023 • Fangrui Lv, Jian Liang, Shuang Li, Jinming Zhang, Di Liu
A classical solution to DG is domain augmentation, the common belief of which is that diversifying source domains will be conducive to the out-of-distribution generalization.
1 code implementation • CVPR 2022 • Fangrui Lv, Jian Liang, Shuang Li, Bin Zang, Chi Harold Liu, Ziteng Wang, Di Liu
Specifically, we assume that each input is constructed from a mix of causal factors (whose relationship with the label is invariant across domains) and non-causal factors (category-independent), and only the former cause the classification judgments.
1 code implementation • NeurIPS 2021 • Fangrui Lv, Jian Liang, Kaixiong Gong, Shuang Li, Chi Harold Liu, Han Li, Di Liu, Guoren Wang
Domain adaptation (DA) attempts to transfer the knowledge from a labeled source domain to an unlabeled target domain that follows different distribution from the source.
1 code implementation • 6 Dec 2021 • Jian Liang, Fangrui Lv, Di Liu, Zehui Dai, Xu Tian, Shuang Li, Fei Wang, Han Li
Challenges of the problem include 1) how to align large-scale entities between sources to share information and 2) how to mitigate negative transfer from joint learning multi-source data.
1 code implementation • ICCV 2021 • Shuang Li, Mixue Xie, Fangrui Lv, Chi Harold Liu, Jian Liang, Chen Qin, Wei Li
To tackle this issue, we propose Semantic Concentration for Domain Adaptation (SCDA), which encourages the model to concentrate on the most principal features via the pair-wise adversarial alignment of prediction distributions.
1 code implementation • 13 Dec 2020 • Shuang Li, Fangrui Lv, Binhui Xie, Chi Harold Liu, Jian Liang, Chen Qin
Motivated by the observation that target samples cannot always be separated distinctly by the decision boundary, here in the proposed BCDM, we design a novel classifier determinacy disparity (CDD) metric, which formulates classifier discrepancy as the class relevance of distinct target predictions and implicitly introduces constraint on the target feature discriminability.