Inverting Visual Representations with Convolutional Networks

• Published in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 4829 - 4837
• Main Authors: Dosovitskiy, Alexey, Brox, Thomas
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2016
• Subjects: Computer architecture; Feature extraction; Image color analysis; Image reconstruction; Microprocessors; Neural networks; Training
• ISSN: 1063-6919
• DOI: 10.1109/CVPR.2016.522

Feature representations, both hand-designed and learned ones, are often hard to analyze and interpret, even when they are extracted from visual data. We propose a new approach to study image representations by inverting them with an up-convolutional neural network. We apply the method to shallow rep...