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.
@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}
}