Crucial Semantic Classifier-based Adversarial Learning for Unsupervised Domain Adaptation

TL;DR

This paper introduces CSCAL, a novel adversarial learning approach for unsupervised domain adaptation that emphasizes transferring crucial semantic knowledge using classifier-based discrepancies, improving adaptation without extra networks.

Contribution

It proposes a classifier-based adversarial learning method that implicitly acts as a domain discriminator, enhancing semantic transfer in UDA without additional network components.

Findings

Improves UDA performance by focusing on crucial semantic knowledge.

Uses Paired-Level Discrepancy for intra-class alignment.

Employs Nuclear Norm-based Discrepancy for inter-class information.

Abstract

Unsupervised Domain Adaptation (UDA), which aims to explore the transferrable features from a well-labeled source domain to a related unlabeled target domain, has been widely progressed. Nevertheless, as one of the mainstream, existing adversarial-based methods neglect to filter the irrelevant semantic knowledge, hindering adaptation performance improvement. Besides, they require an additional domain discriminator that strives extractor to generate confused representations, but discrete designing may cause model collapse. To tackle the above issues, we propose Crucial Semantic Classifier-based Adversarial Learning (CSCAL), which pays more attention to crucial semantic knowledge transferring and leverages the classifier to implicitly play the role of domain discriminator without extra network designing. Specifically, in intra-class-wise alignment, a Paired-Level Discrepancy (PLD) is designed to transfer crucial semantic knowledge. Additionally, based on classifier predictions, a Nuclear Norm-based Discrepancy (NND) is formed that considers inter-class-wise information and improves the adaptation performance. Moreover, CSCAL can be effortlessly merged into different UDA methods as a regularizer and dramatically promote their performance.