基于信息流差异的熵检测法，有效识别模型不熟悉的数据。
EOOD: Entropy-based Out-of-distribution Detection
- 通过对比真实与伪异常数据，定位信息流差异显著的网络层。
- 在选定层计算条件熵，作为判断样本是否异常的置信度分数。
- 适用于提升模型在未知数据上的可靠性，适合部署前检测风险。
深度神经网络在遇到分布外（OOD）样本时往往表现过度自信，给实际部署带来挑战。由于神经网络仅在分布内（ID）数据上训练，其对ID与OOD样本的信息流必然存在差异。本文提出一种基于熵的分布外检测框架EOOD：首先利用真实和伪分布外样本，识别出信息流差异最明显的网络层；随后在该层计算条件熵，作为样本的分布外置信度评分。在多种分布内与分布外设置下的全面实验表明，EOOD在分布外检测任务中表现优异，优于现有先进方法。
原文摘要 · Abstract (English)
Deep neural networks (DNNs) often exhibit overconfidence when encountering out-of-distribution (OOD) samples, posing significant challenges for deployment. Since DNNs are trained on in-distribution (ID) datasets, the information flow of ID samples through DNNs inevitably differs from that of OOD samples. In this paper, we propose an Entropy-based Out-Of-distribution Detection (EOOD) framework. EOOD first identifies specific block where the information flow differences between ID and OOD samples are more pronounced, using both ID and pseudo-OOD samples. It then calculates the conditional entropy on the selected block as the OOD confidence score. Comprehensive experiments conducted across various ID and OOD settings demonstrate the effectiveness of EOOD in OOD detection and its superiority over state-of-the-art methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。