基于训练数据的图像异常值合成方法
Image-based Outlier Synthesis With Training Data
AI总结：
针对OOD检测在细粒度、虚假关联场景下依赖外部数据的问题，本文提出无需外部数据的ASCOOD框架，从ID数据合成近流形虚拟异常值，在7个数据集上验证了其多场景下的检测优势。
摘要：
分布外（OOD）检测对于保障深度学习模型在关键应用场景中的安全部署至关重要。深度学习模型常将OOD样本误判为分布内（ID）样本，当训练集存在虚假关联时，这一漏洞会进一步恶化。同样，在细粒度分类场景下，由于细粒度OOD样本与ID样本高度相似，对其进行检测本身就极具挑战性。然而当前OOD检测研究大多聚焦于相对简单的常规场景，即便少数针对上述困难场景的近期研究，也依赖精心筛选或合成的异常值，最终仍需要外部数据。这催生了我们的核心研究问题：我们能否创新出一种完全无需任何外部数据，适用于细粒度场景与存在虚假关联场景的OOD检测训练框架？本研究提出了统一的虚假关联、细粒度与常规OOD检测方法ASCOOD，彻底消除了对外部数据的依赖。首先，我们通过近似破坏不变特征的方式从ID数据中合成虚拟异常值：具体而言，我们向ID输入添加梯度归因值，在放大真实类别logit的同时破坏不变特征，以此合成具有挑战性的近流形虚拟异常值。随后，我们同时激励模型完成ID分类任务、并对虚拟异常值输出预测不确定性，为此我们进一步提出利用经z-score归一化的标准化特征。ASCOOD可有效缓解虚假关联的影响，同时推动模型捕捉细粒度属性。我们在7个数据集上开展了大量实验，与30余种方法进行对比，结果证明了ASCOOD在虚假关联、细粒度及常规场景下的优异性能。
英文摘要：
Out-of-distribution (OOD) detection is critical to ensure the safe deployment of deep learning models in critical applications. Deep learning models can often misidentify OOD samples as in-distribution (ID) samples. This vulnerability worsens in the presence of spurious correlation in the training set. Likewise, in fine-grained classification settings, detection of fine-grained OOD samples becomes inherently challenging due to their high similarity to ID samples. However, current research on OOD detection has focused instead largely on relatively easier (conventional) cases. Even the few recent works addressing these challenging cases rely on carefully curated or synthesized outliers, ultimately requiring external data. This motivates our central research question: ``Can we innovate OOD detection training framework for fine-grained and spurious settings \textbf{without requiring any external data at all?}" In this work, we present a unified \textbf{A}pproach to \textbf{S}purious, fine-grained, and \textbf{C}onventional \textbf{OOD D}etection (\textbf{\ASCOOD}) that eliminates the reliance on external data. First, we synthesize virtual outliers from ID data by approximating the destruction of invariant features. Specifically, we propose to add gradient attribution values to ID inputs to disrupt invariant features while amplifying true-class logit, thereby synthesizing challenging near-manifold virtual outliers. Then, we simultaneously incentivize ID classification and predictive uncertainty towards virtual outliers. For this, we further propose to leverage standardized features with z-score normalization. ASCOOD effectively mitigates impact of spurious correlations and encourages capturing fine-grained attributes. Extensive experiments across \textbf{7} datasets and and comparisons with \textbf{30+} methods demonstrate merit of ASCOOD in spurious, fine-grained and conventional settings.
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。
