Instance-Aware Observer Network for Out-of-Distribution Object Segmentation
This addresses the challenge of fine-grained anomaly localization in semantic segmentation for applications like autonomous driving or medical imaging, though it is incremental as it builds upon existing ObsNet methods.
The paper tackles the problem of precisely locating anomalies in Out-of-Distribution (OOD) object segmentation by extending the ObsNet approach with instance-aware predictions, resulting in accurate disentanglement of in-distribution and OOD objects across three datasets.
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.