Papers › GEN: Pushing the Limits of Softmax-Based Out-of-Distribution Detection
GEN: Pushing the Limits of Softmax-Based Out-of-Distribution Detection
Xixi Liu, Yaroslava Lochman, Christopher Zach
Out-of-distribution (OOD) detection has been extensively studied in order to successfully deploy neural networks, in particular, for safety-critical applications. Moreover, performing OOD detection on large-scale datasets is closer to reality, but is also more challenging. Several approaches need to either access the training data for score design or expose models to outliers during training. Some post-hoc methods are able to avoid the aforementioned constraints, but are less competitive. In this work, we propose Generalized ENtropy score (GEN), a simple but effective entropy-based score function, which can be applied to any pre-trained softmax-based classifier. Its performance is demonstrated on the large-scale ImageNet-1k OOD detection benchmark. It consistently improves the average AUROC across six commonly-used CNN-based and visual transformer classifiers over a number of state-of-the-art post-hoc methods. The average AUROC improvement is at least 3.5%. Furthermore, we used GEN on top of feature-based enhancing methods as well as methods using training statistics to further improve the OOD detection performance. The code is available at: https://github.com/XixiLiu95/GEN.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Out-of-Distribution Detection | ImageNet-1K vs ImageNet-O | GEN | FPR95 | 97.30 | #3 of 3 | Archive leaderboard | report |
| Out-of-Distribution Detection | ImageNet-1k vs OpenImage-O | GEN | AUROC | 80.43 | #7 of 7 | Archive leaderboard | report |
| Out-of-Distribution Detection | ImageNet-1k vs Textures | GEN | FPR95 | 77.93 | #33 of 34 | Archive leaderboard | report |
| Out-of-Distribution Detection | ImageNet-1k vs iNaturalist | GEN | FPR95 | 68.32 | #28 of 28 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections