Understanding learned CNN features through Filter Decoding with Substitution

no code implementations • 16 Nov 2015 • Ivet Rafegas, Maria Vanrell

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.

Understanding trained CNNs by indexing neuron selectivity

no code implementations • 1 Feb 2017 • Ivet Rafegas, Maria Vanrell, Luis A. Alexandre, Guillem Arias

The impressive performance of Convolutional Neural Networks (CNNs) when solving different vision problems is shadowed by their black-box nature and our consequent lack of understanding of the representations they build and how these representations are organized.