OOD感知的监督对比学习
OOD Aware Supervised Contrastive Learning
AI总结：
针对机器学习模型的OOD检测需求，该研究基于监督对比学习框架，通过新增两个对比损失项、设计伪OOD特征生成方法，构建了对OOD数据鲁棒的分类器，在常用基准上取得了SOTA结果。
摘要：
分布外（Out-of-Distribution, OOD）检测是机器学习模型安全部署中的关键问题，用于识别落在训练分布即分布内（in-distribution, ID）数据之外的样本。大多数OOD研究聚焦于用交叉熵（Cross Entropy, CE）训练的分类模型，并试图修复其固有缺陷。在本研究中，我们利用通过监督对比（Supervised Contrastive, SupCon）训练学习到的强大表征，提出一种整体方法来学习对OOD数据鲁棒的分类器。我们在SupCon损失中扩展了两个额外的对比项：第一项将辅助OOD表征推离ID表征，且不对辅助数据之间的相似性施加任何约束；第二项将OOD特征推离现有类原型，同时将ID表征推向其对应的类原型。当辅助OOD数据不可用时，我们提出特征混合技术来高效生成伪OOD特征。我们的方案简单高效，是闭集监督对比表征学习的自然扩展。我们在常用基准上与多种OOD检测方法进行了对比，取得了当前最优的结果。
英文摘要：
Out-of-Distribution (OOD) detection is a crucial problem for the safe deployment of machine learning models identifying samples that fall outside of the training distribution, i.e. in-distribution data (ID). Most OOD works focus on the classification models trained with Cross Entropy (CE) and attempt to fix its inherent issues. In this work we leverage powerful representation learned with Supervised Contrastive (SupCon) training and propose a holistic approach to learn a classifier robust to OOD data. We extend SupCon loss with two additional contrast terms. The first term pushes auxiliary OOD representations away from ID representations without imposing any constraints on similarities among auxiliary data. The second term pushes OOD features far from the existing class prototypes, while pushing ID representations closer to their corresponding class prototype. When auxiliary OOD data is not available, we propose feature mixing techniques to efficiently generate pseudo-OOD features. Our solution is simple and efficient and acts as a natural extension of the closed-set supervised contrastive representation learning. We compare against different OOD detection methods on the common benchmarks and show state-of-the-art results.
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。
