Instance-Aware Observer Network for Out-of-Distribution Object Segmentation

TL;DR

This paper introduces an instance-aware observer network that enhances out-of-distribution object segmentation by integrating object instance knowledge and instance-wise anomaly scoring, leading to more precise localization of anomalies.

Contribution

It extends the ObsNet framework with object instance information and a class-agnostic detector to improve OOD detection accuracy at the pixel level.

Findings

Accurately disentangles in-distribution and OOD objects

Improves anomaly localization precision

Effective across multiple datasets

Abstract

Recent works on predictive uncertainty estimation have shown promising results on Out-Of-Distribution (OOD) detection for semantic segmentation. However, these methods struggle to precisely locate the point of interest in the image, i.e, the anomaly. This limitation is due to the difficulty of finegrained prediction at the pixel level. To address this issue, we build upon the recent ObsNet approach by providing object instance knowledge to the observer. We extend ObsNet by harnessing an instance-wise mask prediction. We use an additional, class agnostic, object detector to filter and aggregate observer predictions. Finally, we predict an unique anomaly score for each instance in the image. We show that our proposed method accurately disentangles in-distribution objects from OOD objects on three datasets.