Enhancing Generic Segmentation With Learned Region Representations

Or Isaacs, Oran Shayer, Michael Lindenbaum; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 12946-12955

Abstract


Deep learning approaches to generic (non-semantic) segmentation have so far been indirect and relied on edge detection. This is in contrast to semantic segmentation, where DNNs are applied directly. We propose an alternative approach called Deep Generic Segmentation (DGS) and try to follow the path used for semantic segmentation. Our main contribution is a new method for learning a pixel-wise representation that reflects segment relatedness. This representation is combined with a CRF to yield the segmentation algorithm. We show that we are able to learn meaningful representations that improve segmentation quality and that the representations themselves achieve state-of-the-art segment similarity scores. The segmentation results are competitive and promising.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Isaacs_2020_CVPR,
author = {Isaacs, Or and Shayer, Oran and Lindenbaum, Michael},
title = {Enhancing Generic Segmentation With Learned Region Representations},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}