Fool me once: robust selective segmentation via out-of-distribution detection with contrastive learning
In this work, a neural network is trained to simultaneously perform segmentation and pixel-wise Out-of-Distribution (OoD) detection, such that the segmentation of unknown regions of scenes can be rejected. This is made possible by leveraging an OoD dataset with a novel contrastive objective and data...
Main Authors: | , , , |
---|---|
Format: | Conference item |
Language: | English |
Published: |
IEEE
2021
|