长尾分布外检测：优先关注尾部
Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to Tail
AI总结：
针对长尾分布外检测中尾部类特征缺失问题，提出PATT方法，利用vMF混合分布和温度缩放生成对比对增强语义，并在推理阶段引入特征校准，在不影响ID分类性能下显著提升OOD检测能力。
摘要：
当前的分布外（OOD）检测方法通常假设分布内（ID）数据是平衡的，而大多数真实世界的数据遵循长尾分布。以往的长尾OOD检测方法通常通过削弱头部类的语义来平衡ID数据。然而，这种削弱会严重影响ID数据的分类准确率。该任务的主要挑战在于尾部类特征的严重缺乏，导致其与OOD数据混淆。为了解决这个问题，我们引入了一种新颖的优先关注尾部（PATT）方法，使用增强而非削弱。我们的主要直觉是使用von Mises-Fisher（vMF）分布的混合来建模ID数据，并使用温度缩放模块来提升ID数据的置信度。这使我们能够生成无限的对比对，隐式地增强ID类的语义，同时促进ID和OOD数据之间的区分。为了在不损害ID数据分类性能的情况下进一步加强OOD数据的检测，我们在推理阶段提出了特征校准。通过从训练集中提取一个优先关注尾部类并降低OOD数据置信度的注意力权重，我们提高了OOD检测能力。大量实验验证了我们的方法在各种基准上优于当前最先进的方法。
英文摘要：
Current out-of-distribution (OOD) detection methods typically assume balanced in-distribution (ID) data, while most real-world data follow a long-tailed distribution. Previous approaches to long-tailed OOD detection often involve balancing the ID data by reducing the semantics of head classes. However, this reduction can severely affect the classification accuracy of ID data. The main challenge of this task lies in the severe lack of features for tail classes, leading to confusion with OOD data. To tackle this issue, we introduce a novel Prioritizing Attention to Tail (PATT) method using augmentation instead of reduction. Our main intuition involves using a mixture of von Mises-Fisher (vMF) distributions to model the ID data and a temperature scaling module to boost the confidence of ID data. This enables us to generate infinite contrastive pairs, implicitly enhancing the semantics of ID classes while promoting differentiation between ID and OOD data. To further strengthen the detection of OOD data without compromising the classification performance of ID data, we propose feature calibration during the inference phase. By extracting an attention weight from the training set that prioritizes the tail classes and reduces the confidence in OOD data, we improve the OOD detection capability. Extensive experiments verified that our method outperforms the current state-of-the-art methods on various benchmarks.
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。
