English

Exploiting Local Feature Patterns for Unsupervised Domain Adaptation

Machine Learning 2018-11-20 v2 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1811.05042,
  title  = {Exploiting Local Feature Patterns for Unsupervised Domain Adaptation},
  author = {Jun Wen and Risheng Liu and Nenggan Zheng and Qian Zheng and Zhefeng Gong and Junsong Yuan},
  journal= {arXiv preprint arXiv:1811.05042},
  year   = {2018}
}

Comments

AAAI-2019 accepted

R2 v1 2026-06-23T05:13:21.857Z