类别对上下分布（分布是否否上下上下分布？
Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-Of-Distribution Generalization
AI总结：
针对分布外泛化中的上下文偏差问题，提出将类别视为变化环境以实现上下文平衡的无标签估计方法，通过最小化类内样本对比损失并保持跨类不变性，有效提升了分类性能。
摘要：
分布外泛化（OOD）的核心在于学习对环境变化的不变性。如果每个类别的上下文分布均匀，OOD问题将变得简单，因为基于“类别对上下文不变”这一潜在原则，上下文可以被轻易去除。然而，收集这种平衡的数据集在实践中是不可行的。在不平衡数据上学习会导致模型偏向上下文，从而损害OOD性能。因此，解决OOD的关键在于实现上下文平衡。我们认为，现有工作中广泛采用的假设——即上下文偏差可以直接标注或从有偏的类别预测中估计——会导致上下文信息不完整甚至错误。相反，我们指出上述原则中被忽视的另一面：上下文对类别也是不变的。这促使我们将已经标注的类别视为变化的环境，从而在无需上下文标签的情况下解决上下文偏差问题。我们通过最小化类内样本相似度的对比损失，并确保该相似度在所有类别间保持不变来实现这一想法。在具有各种上下文偏差和域间隙的基准测试中，我们表明，配备了我们上下文估计方法的简单重加权分类器实现了最先进的性能。我们在附录中提供了理论证明，代码可在 https://github.com/simpleshinobu/IRMCon 获取。
英文摘要：
Out-Of-Distribution generalization (OOD) is all about learning invariance against environmental changes. If the context in every class is evenly distributed, OOD would be trivial because the context can be easily removed due to an underlying principle: class is invariant to context. However, collecting such a balanced dataset is impractical. Learning on imbalanced data makes the model bias to context and thus hurts OOD. Therefore, the key to OOD is context balance. We argue that the widely adopted assumption in prior work, the context bias can be directly annotated or estimated from biased class prediction, renders the context incomplete or even incorrect. In contrast, we point out the everoverlooked other side of the above principle: context is also invariant to class, which motivates us to consider the classes (which are already labeled) as the varying environments to resolve context bias (without context labels). We implement this idea by minimizing the contrastive loss of intra-class sample similarity while assuring this similarity to be invariant across all classes. On benchmarks with various context biases and domain gaps, we show that a simple re-weighting based classifier equipped with our context estimation achieves state-of-the-art performance. We provide the theoretical justifications in Appendix and codes on https://github.com/simpleshinobu/IRMCon.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
