A Fast Learning Algorithm for Image Segmentation with Max-Pooling Convolutional Networks
Computer Vision and Pattern Recognition
2013-02-08 v1
Abstract
We present a fast algorithm for training MaxPooling Convolutional Networks to segment images. This type of network yields record-breaking performance in a variety of tasks, but is normally trained on a computationally expensive patch-by-patch basis. Our new method processes each training image in a single pass, which is vastly more efficient. We validate the approach in different scenarios and report a 1500-fold speed-up. In an application to automated steel defect detection and segmentation, we obtain excellent performance with short training times.
Cite
@article{arxiv.1302.1690,
title = {A Fast Learning Algorithm for Image Segmentation with Max-Pooling Convolutional Networks},
author = {Jonathan Masci and Alessandro Giusti and Dan Cireşan and Gabriel Fricout and Jürgen Schmidhuber},
journal= {arXiv preprint arXiv:1302.1690},
year = {2013}
}