无需标注环境，通过表示空间特性自动推断环境提升域泛化。
Invariant Learning with Annotation-free Environments
- 从预训练模型的表示空间中挖掘环境信息，无需额外标注。
- 在ColoredMNIST上性能媲美需环境标签的方法。
- 适合缺乏环境标注但需提升泛化能力的场景。
不变学习相比经验风险最小化（ERM）在提升域泛化方面表现更优。然而，多数不变学习方法依赖于训练样本已知环境划分的假设。本文提出一种无需额外标注即可推断环境的新方法，基于对训练后ERM模型表示空间特性的观察。在ColoredMNIST基准上验证了该方法的初步有效性，性能与需要显式环境标签的方法相当，并达到一种对参考模型有强限制的无标注方法的水平。
原文摘要 · Abstract (English)
Invariant learning is a promising approach to improve domain generalization compared to Empirical Risk Minimization (ERM). However, most invariant learning methods rely on the assumption that training examples are pre-partitioned into different known environments. We instead infer environments without the need for additional annotations, motivated by observations of the properties within the representation space of a trained ERM model. We show the preliminary effectiveness of our approach on the ColoredMNIST benchmark, achieving performance comparable to methods requiring explicit environment labels and on par with an annotation-free method that poses strong restrictions on the ERM reference model.
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。