Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detection
This addresses the critical safety issue of misclassifying unknown objects in autonomous driving, representing a strong specific gain rather than a foundational advance.
The paper tackles the problem of pixel-wise out-of-distribution detection in semantic segmentation for autonomous driving, where existing methods confuse rare known objects with unknown ones, and introduces an uncertainty-aware likelihood ratio estimation method that achieves a 2.5% false positive rate and 90.91% average precision on five benchmarks.
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.