%0 Journal Article
%T A Fast Learning Algorithm for Image Segmentation with Max-Pooling Convolutional Networks
%A Jonathan Masci
%A Alessandro Giusti
%A Dan Cire£¿an
%A Gabriel Fricout
%A J¨¹rgen Schmidhuber
%J Computer Science
%D 2013
%I arXiv
%X 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.
%U http://arxiv.org/abs/1302.1690v1