A fast learning algorithm for image segmentation with max-pooling convolutional networks

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Masci, Jonathan, Giusti, Alessandro, Ciresan, Dan, Fricout, Gabriel, Schmidhuber, Jurgen
Format: Conference Proceeding
Language:English
Subjects:
Convolutional Network
Detection
Industrial Application
Medical Imaging
Segmentation
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1522-4880
2381-8549
DOI:10.1109/ICIP.2013.6738559