Image Segmentation by Cascaded Region Agglomeration

Zhile Ren, Gregory Shakhnarovich; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 2011-2018


We propose a hierarchical segmentation algorithm that starts with a very fine oversegmentation and gradually merges regions using a cascade of boundary classifiers. This approach allows the weights of region and boundary features to adapt to the segmentation scale at which they are applied. The stages of the cascade are trained sequentially, with asymetric loss to maximize boundary recall. On six segmentation data sets, our algorithm achieves best performance under most region-quality measures, and does it with fewer segments than the prior work. Our algorithm is also highly competitive in a dense oversegmentation (superpixel) regime under boundary-based measures.

Related Material

author = {Ren, Zhile and Shakhnarovich, Gregory},
title = {Image Segmentation by Cascaded Region Agglomeration},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2013}