Exploiting Local Feature Patterns for Unsupervised Domain Adaptation

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.

arXiv commentAAAI-2019 accepted

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Conditional Generative Adversarial Nets
• Learning Transferable Features with Deep Adaptation Networks
• Improved Training of Wasserstein GANs
• Adversarial Discriminative Domain Adaptation
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Wasserstein Distance Guided Representation Learning for Domain Adaptation
• Few-Shot Adversarial Domain Adaptation
• Multi-Adversarial Domain Adaptation
• Exploiting Local Features from Deep Networks for Image Retrieval