English

Maskomaly:Zero-Shot Mask Anomaly Segmentation

Computer Vision and Pattern Recognition 2023-08-29 v2

Abstract

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.

Keywords

Cite

@article{arxiv.2305.16972,
  title  = {Maskomaly:Zero-Shot Mask Anomaly Segmentation},
  author = {Jan Ackermann and Christos Sakaridis and Fisher Yu},
  journal= {arXiv preprint arXiv:2305.16972},
  year   = {2023}
}

Comments

BMVC 2023

R2 v1 2026-06-28T10:47:36.584Z