Papers › Unmasking Anomalies in Road-Scene Segmentation

Unmasking Anomalies in Road-Scene Segmentation

25 Jul 2023ICCV 2023 1arXiv:2307.13316archive 2025-07-28

Shyam Nandan Rai, Fabio Cermelli, Dario Fontanel, Carlo Masone, Barbara Caputo

Anomaly segmentation is a critical task for driving applications, and it is approached traditionally as a per-pixel classification problem. However, reasoning individually about each pixel without considering their contextual semantics results in high uncertainty around the objects' boundaries and numerous false positives. We propose a paradigm change by shifting from a per-pixel classification to a mask classification. Our mask-based method, Mask2Anomaly, demonstrates the feasibility of integrating an anomaly detection method in a mask-classification architecture. Mask2Anomaly includes several technical novelties that are designed to improve the detection of anomalies in masks: i) a global masked attention module to focus individually on the foreground and background regions; ii) a mask contrastive learning that maximizes the margin between an anomaly and known classes; and iii) a mask refinement solution to reduce false positives. Mask2Anomaly achieves new state-of-the-art results across a range of benchmarks, both in the per-pixel and component-level evaluations. In particular, Mask2Anomaly reduces the average false positives rate by 60% wrt the previous state-of-the-art. Github page: https://github.com/shyam671/Mask2Anomaly-Unmasking-Anomalies-in-Road-Scene-Segmentation.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

shyam671/mask2anomaly-unmasking-anomalies-in-road-scene-segmentation officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Anomaly DetectionAnomaly SegmentationClassificationContrastive LearningInstance SegmentationObject DetectionScene SegmentationSegmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection Fishyscapes Mask2Anomaly AP 95.20 #2 of 8 Archive leaderboard report
Anomaly Detection Fishyscapes Mask2Anomaly FPR95 0.82 #2 of 8 Archive leaderboard report
Anomaly Detection Fishyscapes L&F Mask2Anomaly AP 46.04 #6 of 18 Archive leaderboard report
Anomaly Detection Fishyscapes L&F Mask2Anomaly FPR95 4.36 #6 of 18 Archive leaderboard report
Anomaly Detection Lost and Found Mask2Anomaly AP 86.59 #1 of 4 Archive leaderboard report
Anomaly Detection Lost and Found Mask2Anomaly FPR 5.75 #1 of 4 Archive leaderboard report
Anomaly Detection Road Anomaly Mask2Anomaly AP 79.70 #5 of 10 Archive leaderboard report
Anomaly Detection Road Anomaly Mask2Anomaly FPR95 13.45 #5 of 10 Archive leaderboard report
Instance Segmentation OoDIS Mask2Anomaly AP 13.73 #2 of 3 Archive leaderboard report
Instance Segmentation OoDIS Mask2Anomaly AP50 24.30 #2 of 3 Archive leaderboard report
Object Detection OoDIS Mask2Anomaly AP 1.24 #2 of 3 Archive leaderboard report
Object Detection OoDIS Mask2Anomaly AP50 2.23 #2 of 3 Archive leaderboard report
Scene Segmentation StreetHazards Mask2Anomaly Open-mIoU 59.8 #1 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Contrastive LearningFocus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections