Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908475312832512 |
|---|---|
| author | Hölle, Marc Kellermann, Walter Belagiannis, Vasileios |
| author_facet | Hölle, Marc Kellermann, Walter Belagiannis, Vasileios |
| contents | 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. Code is available at https://github.com/glasbruch/ULRE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_00587 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detection Hölle, Marc Kellermann, Walter Belagiannis, Vasileios Computer Vision and Pattern Recognition 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. Code is available at https://github.com/glasbruch/ULRE. |
| title | Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.00587 |