Unmasking Anomalies in Road-Scene Segmentation

TL;DR

This paper introduces Mask2Anomaly, a novel mask-based approach for anomaly segmentation in road scenes that significantly improves detection accuracy and reduces false positives by leveraging mask classification techniques.

Contribution

It proposes a new paradigm shift from per-pixel to mask classification for anomaly detection, with technical innovations like masked attention, contrastive learning, and mask refinement.

Findings

Achieves state-of-the-art results on multiple benchmarks.

Reduces false positive rate by 60%.

Effectively integrates anomaly detection into mask classification architecture.

Abstract

Anomaly segmentation is a critical task for driving applications, and it is approached traditionally as a per-pixel classification problem. However, reasoning individually about each pixel without considering their contextual semantics results in high uncertainty around the objects' boundaries and numerous false positives. We propose a paradigm change by shifting from a per-pixel classification to a mask classification. Our mask-based method, Mask2Anomaly, demonstrates the feasibility of integrating an anomaly detection method in a mask-classification architecture. Mask2Anomaly includes several technical novelties that are designed to improve the detection of anomalies in masks: i) a global masked attention module to focus individually on the foreground and background regions; ii) a mask contrastive learning that maximizes the margin between an anomaly and known classes; and iii) a mask refinement solution to reduce false positives. Mask2Anomaly achieves new state-of-the-art results across a range of benchmarks, both in the per-pixel and component-level evaluations. In particular, Mask2Anomaly reduces the average false positives rate by 60% wrt the previous state-of-the-art. Github page: https://github.com/shyam671/Mask2Anomaly-Unmasking-Anomalies-in-Road-Scene-Segmentation.