Prototype Guided Network for Anomaly Segmentation

TL;DR

This paper introduces PGAN, a prototype-guided network that enhances anomaly segmentation by modeling semantic prototypes to distinguish in-distribution and OOD pixels, achieving state-of-the-art results.

Contribution

The paper proposes a novel PGAN model that extracts semantic prototypes from limited data to improve anomaly segmentation and OOD pixel recognition.

Findings

Achieved 53.4% mIoU on StreetHazards dataset.

Demonstrated state-of-the-art performance in anomaly segmentation.

Prototypes effectively distinguish in-distribution and OOD pixels.

Abstract

Semantic segmentation methods can not directly identify abnormal objects in images. Anomaly Segmentation algorithm from this realistic setting can distinguish between in-distribution objects and Out-Of-Distribution (OOD) objects and output the anomaly probability for pixels. In this paper, a Prototype Guided Anomaly segmentation Network (PGAN) is proposed to extract semantic prototypes for in-distribution training data from limited annotated images. In the model, prototypes are used to model the hierarchical category semantic information and distinguish OOD pixels. The proposed PGAN model includes a semantic segmentation network and a prototype extraction network. Similarity measures are adopted to optimize the prototypes. The learned semantic prototypes are used as category semantics to compare the similarity with features extracted from test images and then to generate semantic segmentation prediction. The proposed prototype extraction network can also be integrated into most semantic segmentation networks and recognize OOD pixels. On the StreetHazards dataset, the proposed PGAN model produced mIoU of 53.4% for anomaly segmentation. The experimental results demonstrate PGAN may achieve the SOTA performance in the anomaly segmentation tasks.