What makes an object an object? On a practical level, for computer analysis, what we have available is manual or “ground truth” stereotypes but what is better is connected pixels. It’s part of the problem of “Salient Object Segmentation”. ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient Segmentation Michael Kampffmeyer, Nanqing Dong, Xiaodan Liang, Yujia Zhang, Eric P. Xing https://arxiv.org/abs/1804.07836

What makes an object an object? On a practical level, for computer analysis, what we have available is manual or “ground truth” stereotypes but what is better is connected pixels.
 
It’s part of the problem of “Salient Object Segmentation”.
 
ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient Segmentation
 
Michael Kampffmeyer, Nanqing Dong, Xiaodan Liang, Yujia Zhang, Eric P. Xing
 
https://arxiv.org/abs/1804.07836

Leave a comment

Your email address will not be published. Required fields are marked *


6 × = forty eight

Leave a Reply