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

Maskomaly:Zero-Shot Mask Anomaly Segmentation

About

We present a simple and practical framework for anomaly segmentation called Maskomaly. It builds upon mask-based standard semantic segmentation networks by adding a simple inference-time post-processing step which leverages the raw mask outputs of such networks. Maskomaly does not require additional training and only adds a small computational overhead to inference. Most importantly, it does not require anomalous data at training. We show top results for our method on SMIYC, RoadAnomaly, and StreetHazards. On the most central benchmark, SMIYC, Maskomaly outperforms all directly comparable approaches. Further, we introduce a novel metric that benefits the development of robust anomaly segmentation methods and demonstrate its informativeness on RoadAnomaly.

Jan Ackermann, Christos Sakaridis, Fisher Yu• 2023

Related benchmarks

TaskDatasetResultRank
Anomaly SegmentationFishyscapes Static (val)
FPR950.4085
67
Anomaly SegmentationRoad Anomaly
AP73.19
23
Anomaly SegmentationFS-LaF (val)
AP17.2
14
Anomaly SegmentationSMIYC RA 21 (val)
sIoU55.4
13
Anomaly SegmentationSMIYC Obstacle (val)
AUPR88.47
11
Showing 5 of 5 rows

Other info

Follow for update