Maskomaly: Zero-Shot Mask Anomaly Segmentation
Jan Ackermann (ETH Zurich),* Christos Sakaridis (ETH Zurich), Fisher Yu (ETH Zurich)
The 34th British Machine Vision Conference
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.Video
Citation
@inproceedings{Ackermann_2023_BMVC,
author = {Jan Ackermann and Christos Sakaridis and Fisher Yu},
title = {Maskomaly: Zero-Shot Mask Anomaly Segmentation},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0329.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by