Maskomaly:Zero-Shot Mask Anomaly Segmentation

TL;DR

Maskomaly is a zero-shot anomaly segmentation framework that enhances standard segmentation networks with a simple post-processing step, achieving top results without additional training or anomalous data.

Contribution

It introduces a training-free, post-processing method for anomaly segmentation that leverages raw mask outputs, improving performance on multiple benchmarks.

Findings

Outperforms comparable approaches on SMIYC benchmark

Achieves top results with no additional training or anomalous data

Introduces a new metric for evaluating anomaly segmentation methods

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.