Diagnosing Pretrained Models for Out-of-distribution Detection

Haipeng Xiong, Kai Xu, Angela Yao; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025, pp. 1836-1845

This work questions a common assumption of OOD detection, that models with higher in-distribution (ID) accuracy tend to have better OOD performance. Recent findings show this assumption doesn't always hold. A direct observation is that the later version of torchvision models improves ID accuracy but suffers from a significant drop in OOD performance. We systematically diagnose torchvision training recipes and explain this effect by analyzing the maximal logits of ID and OOD samples. We then propose post-hoc and training-time solutions to mitigate the OOD decrease by fixing problematic augmentations in torchvision recipes. Both solutions enhance OOD detection and maintain strong ID performance.