Pith. sign in

Exploiting Both Domain-specific and Invariant Knowledge via a Win-win Transformer for Unsupervised Domain Adaptation

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Most existing UDA approaches enable knowledge transfer via learning domain-invariant representation and sharing one classifier across two domains. However, ignoring the domain-specific information that are related to the task, and forcing a unified classifier to fit both domains will limit the feature expressiveness in each domain. In this paper, by observing that the Transformer architecture with comparable parameters can generate more transferable representations than CNN counterparts, we propose a Win-Win TRansformer framework (WinTR) that separately explores the domain-specific knowledge for each domain and meanwhile interchanges cross-domain knowledge. Specifically, we learn two different mappings using two individual classification tokens in the Transformer, and design for each one a domain-specific classifier. The cross-domain knowledge is transferred via source guided label refinement and single-sided feature alignment with respect to source or target, which keeps the integrity of domain-specific information. Extensive experiments on three benchmark datasets show that our method outperforms the state-of-the-art UDA methods, validating the effectiveness of exploiting both domain-specific and invariant

fields

cs.CV 1

years

2024 1

verdicts

REJECT 1

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper.

  • TransAdapter: Vision Transformer for Feature-Centric Unsupervised Domain Adaptation cs.CV · 2024-12-05 · reject · none · ref 30 · internal anchor

    TransAdapter is a Swin Transformer architecture with graph-based domain discrimination, entropy-reweighted dual attention, and cross-feature transforms that reports state-of-the-art unsupervised domain adaptation results on Office-31, Office-Home, VisDA-2017, and DomainNet.