Exploiting Local Feature Patterns for Unsupervised Domain Adaptation

Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature alignment by matching source and target holistic feature distributions, without considering local features and their multi-mode statistics. We show that the learned local feature patterns are more generic and transferable and a further local feature distribution matching enables fine-grained feature alignment. In this paper, we present a method for learning domain-invariant local feature patterns and jointly aligning holistic and local feature statistics. Comparisons to the state-of-the-art unsupervised domain adaptation methods on two popular benchmark datasets demonstrate the superiority of our approach and its effectiveness on alleviating negative transfer.

Authors

• Jun Wen
• Risheng Liu Dalian University of Technology
• Nenggan Zheng Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou, Zhejiang, China College of Computer Science and Techology, Zhejiang University, Hangzhou, Zhejiang, China State Key Lab of Brain-Machine Intelligence, Zhejiang University, Hangzhou, Zhejiang, China CCAI by MOE and Zhejiang Provincial Government(ZJU), Hangzhou, Zhejiang, China
• Qian Zheng Zhejiang University
• Zhefeng Gong
• Junsong Yuan University at Buffalo

Keywords

No keywords are indexed for this paper.