通过视觉语言模型对齐特征，提升小样本跨域泛化能力。
SemAlign: Language Guided Semi-supervised Domain Generalization
- 用视觉语言模型引导特征对齐，增强领域不变性。
- 在四个基准上达到当前最优性能，显著优于已有方法。
- 适合需要少标注数据下跨域泛化的研究与应用。
半监督领域泛化（SSDG）旨在仅用少量标注数据的情况下，使模型在未见目标域上具备良好泛化能力。现有方法过分关注伪标签（PL）精度，忽视了训练过程中对数据的充分利用，限制了性能提升。本文提出一种新方法：将模型中间特征与视觉语言模型（VLM）的语义丰富且通用的特征空间对齐，以促进领域不变性。同时结合有效的图像级增强和输出层正则化策略，提升数据利用率并减少过拟合。在四个基准上的大量实验表明，该方法在定性和定量上均达到当前最优（SOTA）结果。代码将公开。
原文摘要 · Abstract (English)
Semi-supervised Domain Generalization (SSDG) addresses the challenge of generalizing to unseen target domains with limited labeled data. Existing SSDG methods highlight the importance of achieving high pseudo-labeling (PL) accuracy and preventing model overfitting as the main challenges in SSDG. In this light, we show that the SSDG literature's excessive focus on PL accuracy, without consideration for maximum data utilization during training, limits potential performance improvements. We propose a novel approach to the SSDG problem by aligning the intermediate features of our model with the semantically rich and generalized feature space of a Vision Language Model (VLM) in a way that promotes domain-invariance. The above approach is enhanced with effective image-level augmentation and output-level regularization strategies to improve data utilization and minimize overfitting. Extensive experimentation across four benchmarks against existing SSDG baselines suggests that our method achieves SOTA results both qualitatively and quantitatively. The code will be made publicly available.
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。