Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Road-Aware Anomaly Segmentation with Query-Guided Polygons and CLIP in Autonomous Driving

About

Traditional semantic segmentation models operate under a closed-set assumption and struggle to recognize unknown or unexpected objects-an essential capability for autonomous driving. As a result, such models often misclassify or overlook out-of-distribution (OOD) road anomalies, posing safety risks in open-world environments. We present a lightweight, postprocessing, road-aware anomaly segmentation framework that requires no retraining, no OOD data, and no auxiliary supervision. Our approach builds on a mask transformer-based segmentation network by exploiting query-level mask confidence and deriving a polygonal road prior to detect gap regions that may correspond to anomalies. To further suppress false positives, we introduce a CLIP-based zero-shot semantic filtering module using in-distribution prompts, with optional generalized OOD prompts. By jointly leveraging spatial priors and semantic verification, our framework produces robust and interpretable anomaly predictions. Evaluation on three public benchmarks-Fishyscapes, SMIYC, and RoadAnomaly-shows consistently strong performance. In particular, our method outperforms the training-free baseline Maskomaly on most metrics and achieves the highest AP on Fishyscapes LostAndFound. These results demonstrate the practicality and deployability of our approach for real-world autonomous driving systems.

Zhiran Yan, Gordon Elger• 2026

Related benchmarks

TaskDatasetResultRank
Anomaly SegmentationFishyscapes Static (val)
FPR950.3163
67
Anomaly SegmentationRoad Anomaly
AP75.56
23
Anomaly SegmentationFS-LaF (val)
AP75.01
14
Anomaly SegmentationSMIYC Obstacle (val)
AUPR93.15
11
Showing 4 of 4 rows

Other info

Follow for update