Domain Adaptation via Bidirectional Cross-Attention Transformer
This work addresses the problem of domain adaptation for computer vision, offering an incremental improvement by applying a novel transformer-based method to a known bottleneck.
The paper tackles domain adaptation by proposing a Bidirectional Cross-Attention Transformer (BCAT) to learn domain-invariant features, achieving superior performance on four benchmark datasets compared to existing state-of-the-art methods.
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 mixup 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.