Self-Adversarial Disentangling for Specific Domain Adaptation.

Zhou, Qianyu ORCID: 0000-0002-5331-050X, Gu, Qiqi, Pang, Jiangmiao, Lu, Xuequan ORCID: 0000-0003-0959-408X and Ma, Lizhuang (2023) Self-Adversarial Disentangling for Specific Domain Adaptation. IEEE transactions on pattern analysis and machine intelligence, 45 (7). pp. 8954-8968.

Access the full-text of this item by clicking on the Open Access link.

Official URL: http://dx.doi.org/10.1109/tpami.2023.3238727

Abstract

Domain adaptation aims to bridge the domain shifts between the source and the target domain. These shifts may span different dimensions such as fog, rainfall, etc. However, recent methods typically do not consider explicit prior knowledge about the domain shifts on a specific dimension, thus leading to less desired adaptation performance. In this article, we study a practical setting called Specific Domain Adaptation (SDA) that aligns the source and target domains in a demanded-specific dimension. Within this setting, we observe the intra-domain gap induced by different domainness (i.e., numerical magnitudes of domain shifts in this dimension) is crucial when adapting to a specific domain. To address the problem, we propose a novel Self-Adversarial Disentangling (SAD) framework. In particular, given a specific dimension, we first enrich the source domain by introducing a domainness creator with providing additional supervisory signals. Guided by the created domainness, we design a self-adversarial regularizer and two loss functions to jointly disentangle the latent representations into domainness-specific and domainness-invariant features, thus mitigating the intra-domain gap. Our method can be easily taken as a plug-and-play framework and does not introduce any extra costs in the inference time. We achieve consistent improvements over state-of-the-art methods in both object detection and semantic segmentation.

Item Type:	Article
Divisions:	Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User:	Symplectic Admin
Date Deposited:	14 Mar 2023 09:07
Last Modified:	18 Mar 2024 03:29
DOI:	10.1109/tpami.2023.3238727
Open Access URL:	https://arxiv.org/pdf/2108.03553v1.pdf
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3169036