ReSeg: A Recurrent Neural Network for Object Segmentation

Abstract

We propose a structured prediction architecture for images centered around deep recurrent neural networks. The proposed network, called ReSeg, is based on the recently introduced ReNet model for object classification. We modify and extend it to perform object segmentation, noting that the avoidance of pooling can greatly simplify pixel-wise tasks for images… (More)

Topics

2 Figures and Tables

Statistics

010020020162017
Citations per Year

Citation Velocity: 78

Averaging 78 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.

Cite this paper

@article{Visin2015ReSegAR, title={ReSeg: A Recurrent Neural Network for Object Segmentation}, author={Francesco Visin and Kyle Kastner and Aaron C. Courville and Yoshua Bengio and Matteo Matteucci and Kyunghyun Cho}, journal={CoRR}, year={2015}, volume={abs/1511.07053} }