Domain Adaptation via Bidirectional Cross-Attention Transformer

01/15/2022
by   Xiyu Wang, et al.
0

Domain Adaptation (DA) aims to leverage the knowledge learned from a source domain with ample labeled data to a target domain with unlabeled data only. Most existing studies on DA contribute to learning domain-invariant feature representations for both domains by minimizing the domain gap based on convolution-based neural networks. Recently, vision transformers significantly improved performance in multiple vision tasks. Built on vision transformers, in this paper we propose a Bidirectional Cross-Attention Transformer (BCAT) for DA with the aim to improve the performance. In the proposed BCAT, the attention mechanism can extract implicit source and target mix-up feature representations to narrow the domain discrepancy. Specifically, in BCAT, we design a weight-sharing quadruple-branch transformer with a bidirectional cross-attention mechanism to learn domain-invariant feature representations. Extensive experiments demonstrate that the proposed BCAT model achieves superior performance on four benchmark datasets over existing state-of-the-art DA methods that are based on convolutions or transformers.

READ FULL TEXT
research
08/12/2021

TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) aims to transfer the knowledge lear...
research
02/24/2022

Towards Unsupervised Domain Adaptation via Domain-Transformer

As a vital problem in pattern analysis and machine intelligence, Unsuper...
research
08/27/2023

Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation

Conventional Domain Adaptation (DA) methods aim to learn domain-invarian...
research
07/16/2023

Domain Generalisation with Bidirectional Encoder Representations from Vision Transformers

Domain generalisation involves pooling knowledge from source domain(s) i...
research
10/06/2021

Dynamically Decoding Source Domain Knowledge For Unseen Domain Generalization

Domain generalization is an important problem which has gain much attent...
research
04/16/2022

Safe Self-Refinement for Transformer-based Domain Adaptation

Unsupervised Domain Adaptation (UDA) aims to leverage a label-rich sourc...
research
05/14/2020

Domain Conditioned Adaptation Network

Tremendous research efforts have been made to thrive deep domain adaptat...

Please sign up or login with your details

Forgot password? Click here to reset