Papers › Pixel-wise Anomaly Detection in Complex Driving Scenes

Pixel-wise Anomaly Detection in Complex Driving Scenes

9 Mar 2021CVPR 2021 1arXiv:2103.05445archive 2025-07-28

Giancarlo Di Biase, Hermann Blum, Roland Siegwart, Cesar Cadena

The inability of state-of-the-art semantic segmentation methods to detect anomaly instances hinders them from being deployed in safety-critical and complex applications, such as autonomous driving. Recent approaches have focused on either leveraging segmentation uncertainty to identify anomalous areas or re-synthesizing the image from the semantic label map to find dissimilarities with the input image. In this work, we demonstrate that these two methodologies contain complementary information and can be combined to produce robust predictions for anomaly segmentation. We present a pixel-wise anomaly detection framework that uses uncertainty maps to improve over existing re-synthesis methods in finding dissimilarities between the input and generated images. Our approach works as a general framework around already trained segmentation networks, which ensures anomaly detection without compromising segmentation accuracy, while significantly outperforming all similar methods. Top-2 performance across a range of different anomaly datasets shows the robustness of our approach to handling different anomaly instances.

PaperPDFConference PDFCode

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

Code

giandbt/synboost officialmentioned 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 SegmentationAutonomous DrivingSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection Fishyscapes Synboost AP 72.59 #4 of 8 Archive leaderboard report
Anomaly Detection Fishyscapes Synboost FPR95 18.75 #4 of 8 Archive leaderboard report
Anomaly Detection Fishyscapes L&F SynBoost AP 43.22 #9 of 18 Archive leaderboard report
Anomaly Detection Fishyscapes L&F SynBoost FPR95 15.79 #9 of 18 Archive leaderboard report
Anomaly Detection Lost and Found SynBoost AP 70.43 #3 of 4 Archive leaderboard report
Anomaly Detection Lost and Found SynBoost FPR 4.89 #3 of 4 Archive leaderboard report
Anomaly Detection Road Anomaly Synboost AP 41.83 #8 of 10 Archive leaderboard report
Anomaly Detection Road Anomaly Synboost FPR95 59.72 #8 of 10 Archive leaderboard report
Semantic Segmentation Cityscapes val SynBoost mIoU 83.5 #25 of 99 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.

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