Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detection

Hölle M, Kellermann W, Belagiannis V (2025)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2025

Pages Range: 772-782

Conference Proceedings Title: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops

Event location: Honolulu, HI US

Open Access Link: https://openaccess.thecvf.com/content/ICCV2025W/2COOOL/html/Holle_Uncertainty-Aware_Likelihood_Ratio_Estimation_for_Pixel-Wise_Out-of-Distribution_Detection_ICCVW_2025_paper.html

Abstract

Semantic segmentation models trained on known object classes often fail in real-world autonomous driving scenarios by confidently misclassifying unknown objects. While pixel-wise out-of-distribution detection can identify unknown objects, existing methods struggle in complex scenes where rare object classes are often confused with truly unknown objects. We introduce an uncertainty-aware likelihood ratio estimation method that addresses these limitations. Our approach uses an evidential classifier within a likelihood ratio test to distinguish between known and unknown pixel features from a semantic segmentation model, while explicitly accounting for uncertainty. Instead of producing point estimates, our method outputs probability distributions that capture uncertainty from both rare training examples and imperfect synthetic outliers. We show that by incorporating uncertainty in this way, outlier exposure can be leveraged more effectively. Evaluated on five standard benchmark datasets, our method achieves the lowest average false positive rate (2.5%) among state-of-the-art while maintaining high average precision (90.91%) and incurring only negligible computational overhead.

Authors with CRIS profile

Marc Hölle Professur für Maschinelles Lernen in der Signalverarbeitung Walter Kellermann Technische Fakultät Vasileios Belagiannis Professur für Maschinelles Lernen in der Signalverarbeitung

How to cite

APA:

Hölle, M., Kellermann, W., & Belagiannis, V. (2025). Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detection. In IEEE/CVF (Eds.), Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops (pp. 772-782). Honolulu, HI, US.

MLA:

Hölle, Marc, Walter Kellermann, and Vasileios Belagiannis. "Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detection." Proceedings of the International Conference on Computer Vision, Honolulu, HI Ed. IEEE/CVF, 2025. 772-782.

BibTeX: Download