Strong-Weak Integrated Semi-supervision for Unsupervised Single and Multi Target Domain Adaptation

TL;DR

This paper introduces SWISS, a semi-supervised learning strategy for unsupervised domain adaptation that effectively handles both single-target and multi-target scenarios by leveraging strong and weak representative sets and a novel adversarial logit loss.

Contribution

It proposes a novel SWISS framework that integrates strong and weak semi-supervision, extending to multi-target adaptation with class-wise domain relationship exploration and peer scaffolding.

Findings

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

Effectively reduces intra-class divergence with adversarial logit loss.

Demonstrates robustness in both single-target and multi-target domain adaptation tasks.

Abstract

Unsupervised domain adaptation (UDA) focuses on transferring knowledge learned in the labeled source domain to the unlabeled target domain. Despite significant progress that has been achieved in single-target domain adaptation for image classification in recent years, the extension from single-target to multi-target domain adaptation is still a largely unexplored problem area. In general, unsupervised domain adaptation faces a major challenge when attempting to learn reliable information from a single unlabeled target domain. Increasing the number of unlabeled target domains further exacerbate the problem rather significantly. In this paper, we propose a novel strong-weak integrated semi-supervision (SWISS) learning strategy for image classification using unsupervised domain adaptation that works well for both single-target and multi-target scenarios. Under the proposed SWISS-UDA framework, a strong representative set with high confidence but low diversity target domain samples and a weak representative set with low confidence but high diversity target domain samples are updated constantly during the training process. Both sets are fused to generate an augmented strong-weak training batch with pseudo-labels to train the network during every iteration. The extension from single-target to multi-target domain adaptation is accomplished by exploring the class-wise distance relationship between domains and replacing the strong representative set with much stronger samples from peer domains via peer scaffolding. Moreover, a novel adversarial logit loss is proposed to reduce the intra-class divergence between source and target domains, which is back-propagated adversarially with a gradient reverse layer between the classifier and the rest of the network. Experimental results based on three benchmarks, Office-31, Office-Home, and DomainNet, show the effectiveness of the proposed SWISS framework.