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

07/18/2022
by   Victor Besnier, et al.
6

Recent work on Observer Network has shown promising results on Out-Of-Distribution (OOD) detection for semantic segmentation. These methods have difficulty in precisely locating the point of interest in the image, i.e, the anomaly. This limitation is due to the difficulty of fine-grained prediction at the pixel level. To address this issue, we provide instance knowledge to the observer. We extend the approach of 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 disentangle in-distribution objects from Out-Of-Distribution objects on three datasets.

READ FULL TEXT

page 2

page 4

research
09/08/2016

Bottom-up Instance Segmentation using Deep Higher-Order CRFs

Traditional Scene Understanding problems such as Object Detection and Se...
research
08/03/2023

UGainS: Uncertainty Guided Anomaly Instance Segmentation

A single unexpected object on the road can cause an accident or may lead...
research
11/25/2021

Uncertainty Aware Proposal Segmentation for Unknown Object Detection

Recent efforts in deploying Deep Neural Networks for object detection in...
research
01/15/2022

Prototype Guided Network for Anomaly Segmentation

Semantic segmentation methods can not directly identify abnormal objects...
research
07/04/2023

EffSeg: Efficient Fine-Grained Instance Segmentation using Structure-Preserving Sparsity

Many two-stage instance segmentation heads predict a coarse 28x28 mask p...
research
11/27/2018

Affinity Derivation and Graph Merge for Instance Segmentation

We present an instance segmentation scheme based on pixel affinity infor...
research
04/30/2021

SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation

State-of-the-art semantic or instance segmentation deep neural networks ...

Please sign up or login with your details

Forgot password? Click here to reset