GEN: Pushing the Limits of Softmax-Based Out-of-Distribution Detection
Paper in proceeding, 2023

Out-of-distribution (OOD) detection has been exten-sively studied in order to successfully deploy neural networks, in particular, for safety-critical applications. More-over, performing OOD detection on large-scale datasets is closer to reality, but is also more challenging. Sev-eral 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 afore-mentioned 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-lk OOD detection benchmark. It consistently improves the average AUROC across six commonly-used CNN-based and visual transformer classifiers over a num-ber of state-of-the-art post-hoc methods. The average AU- ROC 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.

Deep learning architectures and techniques

Author

Xixi Liu

Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering

Yaroslava Lochman

Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering

Christopher Zach

Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

10636919 (ISSN)

Vol. 2023-June 23946-23955
9798350301298 (ISBN)

IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
Vancouver, Canada,

Learning and Leveraging Rich Priors for Factorization Problems

Wallenberg AI, Autonomous Systems and Software Program, 2020-12-01 -- .

Subject Categories

Computer Engineering

Computer Science

Computer Vision and Robotics (Autonomous Systems)

DOI

10.1109/CVPR52729.2023.02293

More information

Latest update

7/17/2024