通过测试时变形增强提升模型跨域泛化能力
Class-Invariant Test-Time Augmentation for Domain Generalization
- 对输入图像施加弹性与网格变形，保持类别不变
- 用置信度筛选机制融合多幅变形图的预测结果
- 轻量级设计适配各类模型和算法，效果稳定
深度模型在分布偏移下性能常大幅下降。领域泛化（DG）旨在使模型适应未见领域。现有方法多依赖多领域训练或计算昂贵的测试时自适应。本文提出一种轻量级测试时增强策略：类不变测试时增强（CI-TTA）。通过弹性与网格变形生成同一类别的多个输入变体，利用置信度引导的过滤机制聚合预测结果，剔除不可靠输出，确保最终决策基于一致可靠的特征。在PACS与Office-Home数据集上的大量实验表明，该方法在不同DG算法与主干网络上均取得持续提升，验证了其有效性与通用性。
原文摘要 · Abstract (English)
Deep models often suffer significant performance degradation under distribution shifts. Domain generalization (DG) seeks to mitigate this challenge by enabling models to generalize to unseen domains. Most prior approaches rely on multi-domain training or computationally intensive test-time adaptation. In contrast, we propose a complementary strategy: lightweight test-time augmentation. Specifically, we develop a novel Class-Invariant Test-Time Augmentation (CI-TTA) technique. The idea is to generate multiple variants of each input image through elastic and grid deformations that nevertheless belong to the same class as the original input. Their predictions are aggregated through a confidence-guided filtering scheme that remove unreliable outputs, ensuring the final decision relies on consistent and trustworthy cues. Extensive Experiments on PACS and Office-Home datasets demonstrate consistent gains across different DG algorithms and backbones, highlighting the effectiveness and generality of our approach.
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。