通过特征空间语义一致性提升未知域外样本检测能力
Feature-Space Semantic Invariance: Enhanced OOD Detection for Open-Set Domain Generalization
- 在特征空间保持跨域语义一致，统一处理域泛化与未知类检测
- 在ColoredMNIST上使AUROC提升9.1%至18.9%，同时提高分类准确率
- 适合需要兼顾泛化与异常检测的现实场景应用
开集域泛化应对真实世界挑战：模型需在未见域上泛化（域泛化），同时识别训练中未出现的未知类别（开集识别）。然而，现有方法多将两者分开处理，限制了实用性。为此，本文提出统一框架，引入特征空间语义不变性（FSI），在特征空间中保持跨域语义一致性，从而更准确地检测未见域中的域外样本。此外，采用生成模型合成具有新域风格或类别标签的伪数据，增强模型鲁棒性。初步实验表明，该方法在ColoredMNIST上使AUROC提升9.1%至18.9%，同时显著提高分布内分类准确率。
原文摘要 · Abstract (English)
Open-set domain generalization addresses a real-world challenge: training a model to generalize across unseen domains (domain generalization) while also detecting samples from unknown classes not encountered during training (open-set recognition). However, most existing approaches tackle these issues separately, limiting their practical applicability. To overcome this limitation, we propose a unified framework for open-set domain generalization by introducing Feature-space Semantic Invariance (FSI). FSI maintains semantic consistency across different domains within the feature space, enabling more accurate detection of OOD instances in unseen domains. Additionally, we adopt a generative model to produce synthetic data with novel domain styles or class labels, enhancing model robustness. Initial experiments show that our method improves AUROC by 9.1% to 18.9% on ColoredMNIST, while also significantly increasing in-distribution classification accuracy.
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。