Domain Adaptation via Bidirectional Cross-Attention Transformer

• URL: http://arxiv.org/abs/2201.05887v1
• Date: Sat, 15 Jan 2022 16:49:56 GMT
• Title: Domain Adaptation via Bidirectional Cross-Attention Transformer
• Authors: Xiyu Wang, Pengxin Guo, and Yu Zhang
• Abstract summary: We propose a Bidirectional Cross-Attention Transformer (BCAT) for Domain Adaptation (DA) In BCAT, the attention mechanism can extract implicit source and target mix-up feature representations to narrow the domain discrepancy. Experiments demonstrate that the proposed BCAT model achieves superior performance on four benchmark datasets.
• Score: 4.643871270374136
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation [1.9035011984138845]
  Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from labeled source domains to improve performance on unlabeled target domains. Recent research has shown promise in applying Vision Transformers (ViTs) to this task. We propose a novel Feature Fusion Transferability Aware Transformer (FFTAT) to enhance ViT performance in UDA tasks.
  arXiv  Detail & Related papers  (2024-11-10T22:23:12Z)
• Safe Self-Refinement for Transformer-based Domain Adaptation [73.8480218879]
  Unsupervised Domain Adaptation (UDA) aims to leverage a label-rich source domain to solve tasks on a related unlabeled target domain. It is a challenging problem especially when a large domain gap lies between the source and target domains. We propose a novel solution named SSRT (Safe Self-Refinement for Transformer-based domain adaptation), which brings improvement from two aspects.
  arXiv  Detail & Related papers  (2022-04-16T00:15:46Z)
• CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation [44.06904757181245]
  Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to a different unlabeled target domain. One fundamental problem for the category level based UDA is the production of pseudo labels for samples in target domain. We design a two-way center-aware labeling algorithm to produce pseudo labels for target samples. Along with the pseudo labels, a weight-sharing triple-branch transformer framework is proposed to apply self-attention and cross-attention for source/target feature learning and source-target domain alignment.
  arXiv  Detail & Related papers  (2021-09-13T17:59:07Z)
• Deep Adversarial Transition Learning using Cross-Grafted Generative Stacks [3.756448228784421]
  We present a novel "deep adversarial transition learning" (DATL) framework that bridges the domain gap. We construct variational auto-encoders (VAEs) for the two domains, and form bidirectional transitions by cross-grafting the VAEs' decoder stacks. generative adversarial networks (GAN) are employed for domain adaptation, mapping the target domain data to the known label space of the source domain.
  arXiv  Detail & Related papers  (2020-09-25T04:25:27Z)
• Adaptively-Accumulated Knowledge Transfer for Partial Domain Adaptation [66.74638960925854]
  Partial domain adaptation (PDA) deals with a realistic and challenging problem when the source domain label space substitutes the target domain. We propose an Adaptively-Accumulated Knowledge Transfer framework (A$2$KT) to align the relevant categories across two domains.
  arXiv  Detail & Related papers  (2020-08-27T00:53:43Z)
• Domain Conditioned Adaptation Network [90.63261870610211]
  We propose a Domain Conditioned Adaptation Network (DCAN) to excite distinct convolutional channels with a domain conditioned channel attention mechanism. This is the first work to explore the domain-wise convolutional channel activation for deep DA networks.
  arXiv  Detail & Related papers  (2020-05-14T04:23:24Z)
• Supervised Domain Adaptation using Graph Embedding [86.3361797111839]
  Domain adaptation methods assume that distributions between the two domains are shifted and attempt to realign them. We propose a generic framework based on graph embedding. We show that the proposed approach leads to a powerful Domain Adaptation framework.
  arXiv  Detail & Related papers  (2020-03-09T12:25:13Z)
• Towards Fair Cross-Domain Adaptation via Generative Learning [50.76694500782927]
  Domain Adaptation (DA) targets at adapting a model trained over the well-labeled source domain to the unlabeled target domain lying in different distributions. We develop a novel Generative Few-shot Cross-domain Adaptation (GFCA) algorithm for fair cross-domain classification.
  arXiv  Detail & Related papers  (2020-03-04T23:25:09Z)
• Bi-Directional Generation for Unsupervised Domain Adaptation [61.73001005378002]
  Unsupervised domain adaptation facilitates the unlabeled target domain relying on well-established source domain information. Conventional methods forcefully reducing the domain discrepancy in the latent space will result in the destruction of intrinsic data structure. We propose a Bi-Directional Generation domain adaptation model with consistent classifiers interpolating two intermediate domains to bridge source and target domains.
  arXiv  Detail & Related papers  (2020-02-12T09:45:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.