Conference paper

Color Representation in Deep Neural Networks

Convolutional neural networks are top-performers on image classification tasks. Understanding how they make use of color information in images may be useful for various tasks. In this paper we analyze the representation learned by a popular CNN to detect and characterize color-related features. We confirm the existence of some object- and color-specific units, as well as the effect of layer-depth on color-sensitivity and class-invariance.


    • EPFL-CONF-231742

    Record created on 2017-10-12, modified on 2017-11-02

Related material