通过否定消除干扰因素：利用数据增强调整虚假相关性
Nuisances via Negativa: Adjusting for Spurious Correlations via Data Augmentation
AI总结：
本文提出通过破坏语义数据来识别干扰因素与标签的相关性，并据此调整预测，从而在多个分布外任务中提升模型对虚假相关性的鲁棒性。
摘要：
在预测任务中，存在一些特征在不同设置下与标签的关系保持一致；这些特征被称为语义特征或语义。与标签关系变化的特征则是干扰因素。例如，在从自然图像中检测奶牛时，头部形状是语义特征，但由于奶牛图像常常有草地背景但并非总是如此，背景就是一个干扰因素。利用干扰因素与标签关系的模型在这些关系发生变化时会面临性能下降。构建对此类变化具有鲁棒性的模型需要超越特征和标签样本之外的额外知识。例如，现有工作使用干扰因素的标注，或假设经过 ERM 训练的模型依赖于干扰因素。整合新型额外知识的方法扩大了可以构建鲁棒模型的设置范围。我们开发了一种利用语义知识的方法：在数据中破坏语义，然后使用被破坏的数据生成能够识别干扰因素与标签之间相关性的模型。一旦识别出这些相关性，就可以利用它们来调整干扰因素驱动预测的情况。我们研究了语义破坏在多个分布外（OOD）任务中为不同的避免虚假相关性方法提供支持的效果，这些任务包括水鸟分类、自然语言推理（NLI）以及胸部 X 光片中心脏肥大检测。
英文摘要：
In prediction tasks, there exist features that are related to the label in the same way across different settings for that task; these are semantic features or semantics. Features with varying relationships to the label are nuisances. For example, in detecting cows from natural images, the shape of the head is semantic but because images of cows often have grass backgrounds but not always, the background is a nuisance. Models that exploit nuisance-label relationships face performance degradation when these relationships change. Building models robust to such changes requires additional knowledge beyond samples of the features and labels. For example, existing work uses annotations of nuisances or assumes ERM-trained models depend on nuisances. Approaches to integrate new kinds of additional knowledge enlarge the settings where robust models can be built. We develop an approach to use knowledge about the semantics by corrupting them in data, and then using the corrupted data to produce models which identify correlations between nuisances and the label. Once these correlations are identified, they can be used to adjust for where nuisances drive predictions. We study semantic corruptions in powering different spurious-correlation avoiding methods on multiple out-of-distribution (OOD) tasks like classifying waterbirds, natural language inference (NLI), and detecting cardiomegaly in chest X-rays.
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。
