用视觉Transformer提升无监督域适应的特征对齐能力
TransAdapter: Vision Transformer for Feature-Centric Unsupervised Domain Adaptation
- 基于Swin Transformer设计图域判别器与自适应双注意力模块
- 在多个基准上达到当前最优性能，无需特定任务适配模块
- 适合需要跨域泛化且缺乏标注数据的场景
无监督域适应（UDA）旨在利用源域有标签数据解决目标域无标签任务，常受域间差异制约。传统基于CNN的方法难以充分捕捉复杂域关系，促使研究转向视觉变换器（如Swin Transformer），其擅长建模局部与全局依赖。本文提出一种新型UDA方法，基于Swin Transformer设计三个关键模块：图域判别器通过图卷积和熵注意力增强像素间相关性建模；自适应双注意力模块结合窗口与移位窗口注意力并动态重加权，有效对齐长程与局部特征；跨特征变换模块改进Swin块以提升跨域泛化能力。大量实验验证该方法在多种基准上达到领先性能，且无需任务特定对齐模块，展现出强适应性。
原文摘要 · Abstract (English)
Unsupervised Domain Adaptation (UDA) aims to utilize labeled data from a source domain to solve tasks in an unlabeled target domain, often hindered by significant domain gaps. Traditional CNN-based methods struggle to fully capture complex domain relationships, motivating the shift to vision transformers like the Swin Transformer, which excel in modeling both local and global dependencies. In this work, we propose a novel UDA approach leveraging the Swin Transformer with three key modules. A Graph Domain Discriminator enhances domain alignment by capturing inter-pixel correlations through graph convolutions and entropy-based attention differentiation. An Adaptive Double Attention module combines Windows and Shifted Windows attention with dynamic reweighting to align long-range and local features effectively. Finally, a Cross-Feature Transform modifies Swin Transformer blocks to improve generalization across domains. Extensive benchmarks confirm the state-of-the-art performance of our versatile method, which requires no task-specific alignment modules, establishing its adaptability to diverse applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。