UGainS: Uncertainty Guided Anomaly Instance Segmentation

TL;DR

UGainS introduces an uncertainty-guided approach for anomaly instance segmentation in autonomous driving, significantly improving the accuracy of identifying and segmenting anomalous objects on the road.

Contribution

It proposes a novel method combining out-of-distribution uncertainty estimation with a generalist segmentation model to accurately segment individual anomalous objects.

Findings

Achieves AP of 80.08% on Fishyscapes Lost and Found

Achieves AP of 88.98% on RoadAnomaly validation set

Outperforms existing pixel-level anomaly segmentation methods

Abstract

A single unexpected object on the road can cause an accident or may lead to injuries. To prevent this, we need a reliable mechanism for finding anomalous objects on the road. This task, called anomaly segmentation, can be a stepping stone to safe and reliable autonomous driving. Current approaches tackle anomaly segmentation by assigning an anomaly score to each pixel and by grouping anomalous regions using simple heuristics. However, pixel grouping is a limiting factor when it comes to evaluating the segmentation performance of individual anomalous objects. To address the issue of grouping multiple anomaly instances into one, we propose an approach that produces accurate anomaly instance masks. Our approach centers on an out-of-distribution segmentation model for identifying uncertain regions and a strong generalist segmentation model for anomaly instances segmentation. We investigate ways to use uncertain regions to guide such a segmentation model to perform segmentation of anomalous instances. By incorporating strong object priors from a generalist model we additionally improve the per-pixel anomaly segmentation performance. Our approach outperforms current pixel-level anomaly segmentation methods, achieving an AP of 80.08% and 88.98% on the Fishyscapes Lost and Found and the RoadAnomaly validation sets respectively. Project page: https://vision.rwth-aachen.de/ugains