2020/11/07 by Jun Wen, Changjian Shui, Wen, Jun +11 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · Mathematics · Medicine · Psychology · #Artificial intelligence #Cancer-related molecular mechanisms research #Classifier (UML) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Counterfactual thinking #Discriminative model #Domain (mathematical analysis) #Domain Adaptation and Few-Shot Learning #Domain adaptation #FOS: Computer and information sciences #Feature (linguistics) #Focus (optics) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine learning #Mathematics #Pattern recognition (psychology) #Psychology #Respiratory viral infections research #Spurious relationship #Transfer of learning #Transferability #cs.CV #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.2011.03737
published in arXiv (Cornell University) (Cornell University)
arxiv created 2020/11/07 · openalex publication_date 2020/11/07 · arxiv updated 2020/11/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Domain adaptation (DA) aims to transfer discriminative features learned from source domain to target domain. Most of DA methods focus on enhancing feature transferability through domain-invariance learning. However, source-learned discriminability itself might be tailored to be biased and unsafely transferable by spurious correlations, i.e., part of source-specific features are correlated with category labels. We find that standard domain-invariance learning suffers from such correlations and incorrectly transfers the source-specifics. To address this issue, we intervene in the learning of feature discriminability using unlabeled target data to guide it to get rid of the domain-specific part and be safely transferable. Concretely, we generate counterfactual features that distinguish the domain-specifics from domain-sharable part through a novel feature intervention strategy. To prevent the residence of domain-specifics, the feature discriminability is trained to be invariant to the mutations in the domain-specifics of counterfactual features. Experimenting on typical one-to-one unsupervised domain adaptation and challenging domain-agnostic adaptation tasks, the consistent performance improvements of our method over state-of-the-art approaches validate that the learned discriminative features are more safely transferable and generalize well to novel domains.