EOOD: Entropy-based Out-of-distribution Detection
By: Guide Yang , Chao Hou , Weilong Peng and more
Potential Business Impact:
Helps computers know when they see something new.
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.
Similar Papers
Out-of-Distribution Detection from Small Training Sets using Bayesian Neural Network Classifiers
Machine Learning (CS)
Helps AI know when it's unsure.
OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionary
CV and Pattern Recognition
Helps computers spot fake or weird data.
Revisiting Likelihood-Based Out-of-Distribution Detection by Modeling Representations
Machine Learning (CS)
Makes AI better at spotting fake or wrong information.