2015/11/16 by Ivet Rafegas, Rafegas, Ivet, María Vanrell +2
Computer Science · Engineering · #Advanced Neural Network Applications #Algorithm #Artificial intelligence #Artificial neural network #CCD and CMOS Imaging Sensors #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Convolution (computer science) #Convolutional neural network #Decoding methods #Deconvolution #ENCODE #Encoding (memory) #FOS: Computer and information sciences #Filter (signal processing) #Generative Adversarial Networks and Image Synthesis #Neural Networks and Applications #Pattern recognition (psychology) #Representation (politics) #Theoretical computer science #cs.CV
paper · pdf · doi:10.48550/arxiv.1511.05084
published in arXiv (Cornell University) (Cornell University) · 10 pages, 7 figures (including supplementary material). Submitted for review for CVPR 2016
openalex publication_date 2015/11/16 · arxiv created 2015/11/17 · arxiv updated 2015/11/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
In parallel with the success of CNNs to solve vision problems, there is a growing interest in developing methodologies to understand and visualize the internal representations of these networks. How the responses of a trained CNN encode the visual information is a fundamental question both for computer and human vision research. Image representations provided by the first convolutional layer as well as the resolution change provided by the max-polling operation are easy to understand, however, as soon as a second and further convolutional layers are added in the representation, any intuition is lost. A usual way to deal with this problem has been to define deconvolutional networks that somehow allow to explore the internal representations of the most important activations towards the image space, where deconvolution is assumed as a convolution with the transposed filter. However, this assumption is not the best approximation of an inverse convolution. In this paper we propose a new assumption based on filter substitution to reverse the encoding of a convolutional layer. This provides us with a new tool to directly visualize any CNN single neuron as a filter in the first layer, this is in terms of the image space.