Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation

TL;DR

This paper introduces ILA-DA, an instance affinity-based method for unsupervised domain adaptation that improves transfer accuracy by considering class-specific structures during domain alignment.

Contribution

It proposes a novel instance affinity criterion and a multi-sample contrastive loss to enhance domain adaptation by preserving class structures.

Findings

Consistent accuracy improvements over existing methods.

Effective in reducing noisy classifier boundaries.

Applicable across various benchmark datasets.

Abstract

Domain adaptation deals with training models using large scale labeled data from a specific source domain and then adapting the knowledge to certain target domains that have few or no labels. Many prior works learn domain agnostic feature representations for this purpose using a global distribution alignment objective which does not take into account the finer class specific structure in the source and target domains. We address this issue in our work and propose an instance affinity based criterion for source to target transfer during adaptation, called ILA-DA. We first propose a reliable and efficient method to extract similar and dissimilar samples across source and target, and utilize a multi-sample contrastive loss to drive the domain alignment process. ILA-DA simultaneously accounts for intra-class clustering as well as inter-class separation among the categories, resulting in less noisy classifier boundaries, improved transferability and increased accuracy. We verify the effectiveness of ILA-DA by observing consistent improvements in accuracy over popular domain adaptation approaches on a variety of benchmark datasets and provide insights into the proposed alignment approach. Code will be made publicly available at https://github.com/astuti/ILA-DA.