2 papers
cs.CV2019
Enhancing Generic Segmentation with Learned Region Representations
Or Isaacs, Oran Shayer, Michael Lindenbaum
Current successful approaches for generic (non-semantic) segmentation rely mostly on edge detection and have leveraged the strengths of deep learning mainly by improving the edge d…
cs.CV2019
Learning Pixel Representations for Generic Segmentation
Oran Shayer, Michael Lindenbaum
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…