Unsupervised Domain Adaptation via Bidirectional Cross-Attention Transformer

Wang, Xiyu1,2; Guo, Pengxin1; Zhang, Yu1,3

10.1007/978-3-031-43424-2_19

2023

European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

2945-9133

1611-3349

978-3-031-43423-5

MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES: RESEARCH TRACK, ECML PKDD 2023, PT V

14173

SEP 18-22, 2023

null,Turin,ITALY

GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND

SPRINGER INTERNATIONAL PUBLISHING AG

Unsupervised Domain Adaptation (UDA) seeks to utilize the knowledge acquired from a source domain, abundant in labeled data, and apply it to a target domain that contains only unlabeled data. The majority of existing UDA research focuses on learning domain-invariant feature representations for both domains by minimizing the domain gap using convolution-based neural networks. Recently, vision transformers have made significant strides in enhancing performance across various visual tasks. In this paper, we introduce a Bidirectional Cross-Attention Transformer (BCAT) for UDA, which is built upon vision transformers with the goal of improving performance. The proposed BCAT employs an attention mechanism to extract implicit source and target mixup feature representations, thereby reducing the domain discrepancy. More specifically, BCAT is designed as a weight-sharing quadruple-branch transformer with a bidirectional cross-attention mechanism, allowing it to learn domain-invariant feature representations. Comprehensive experiments indicate that our proposed BCAT model outperforms existing state-of-the-art UDA methods, both convolution-based and transformer-based, on four benchmark datasets.

Unsupervised Domain Adaptation Transformer Cross-Attention

第一 ; 通讯

英语

EI ; CPCI-S

NSFC["62136005","62076118"] ; Shenzhen fundamental research program[JCYJ20210324105000003]

Computer Science

Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods

WOS:001156142300019

Web of Science

1.Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China
2.School of Computer Science, Faculty of Engineering, University of Sydney, Camperdown, Australia
3.Peng Cheng Laboratory, Shenzhen, China

Wang, Xiyu,Guo, Pengxin,Zhang, Yu. Unsupervised Domain Adaptation via Bidirectional Cross-Attention Transformer[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2023.