Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation

TL;DR

This paper introduces a novel concurrent subsidiary supervision method for unsupervised source-free domain adaptation, leveraging a supervised subsidiary task to improve adaptation performance without source data access.

Contribution

It proposes a new process of sticker intervention and subsidiary task criteria, enhancing domain adaptation and privacy preservation in source-free settings.

Findings

Outperforms existing methods on Office-31, Office-Home, DomainNet, and VisDA benchmarks.

Effective for both single-source and multi-source source-free DA.

Complementary to existing non-source-free techniques, achieving top results.

Abstract

The prime challenge in unsupervised domain adaptation (DA) is to mitigate the domain shift between the source and target domains. Prior DA works show that pretext tasks could be used to mitigate this domain shift by learning domain invariant representations. However, in practice, we find that most existing pretext tasks are ineffective against other established techniques. Thus, we theoretically analyze how and when a subsidiary pretext task could be leveraged to assist the goal task of a given DA problem and develop objective subsidiary task suitability criteria. Based on this criteria, we devise a novel process of sticker intervention and cast sticker classification as a supervised subsidiary DA problem concurrent to the goal task unsupervised DA. Our approach not only improves goal task adaptation performance, but also facilitates privacy-oriented source-free DA i.e. without concurrent source-target access. Experiments on the standard Office-31, Office-Home, DomainNet, and VisDA benchmarks demonstrate our superiority for both single-source and multi-source source-free DA. Our approach also complements existing non-source-free works, achieving leading performance.