Inverting Visual Representations with Convolutional Networks


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 representations (HOG, SIFT, LBP), as well as to deep networks… (More)
DOI: 10.1109/CVPR.2016.522


13 Figures and Tables


Citations per Year

118 Citations

Semantic Scholar estimates that this publication has 118 citations based on the available data.

See our FAQ for additional information.

Blog articles referencing this paper