EOOD: Entropy-based Out-of-distribution Detection
This addresses a critical safety issue for deploying DNNs in real-world applications by improving OOD detection, though it appears incremental as it builds on existing entropy and information flow concepts.
The paper tackles the problem of deep neural networks being overconfident on out-of-distribution (OOD) samples by proposing an entropy-based detection framework (EOOD) that identifies blocks with pronounced information flow differences and uses conditional entropy for scoring, achieving superior performance over state-of-the-art methods in various settings.
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.