Recurrent Instance Segmentation. (arXiv:1511.08250v1 [cs.CV])

Instance segmentation is the problem of detecting and delineating each object of interest appearing in an image. Current instance segmentation approaches consist of ensembles of modules that are trained independently of each other, thus missing learning opportunities. Here we propose a new instance segmentation paradigm consisting in an end-to-end method that learns how to segment instances sequentially. The model is based on a recurrent neural network that sequentially finds objects and their segmentations one at a time. This net is provided with a spatial memory that keeps track of what pixels have been explained and allows handling occlusion. In order to train the model we designed a new principled loss function that accurately represents the properties of the instance segmentation problem. In the experiments carried out we found that our method outperforms all $5$ state of the art approaches on the Plant Phenotyping dataset.

from cs.AI updates on arXiv.org http://ift.tt/1TfqNCg
via IFTTT