Learning Stable Group Invariant Representations with Convolutional Networks

It is shown that the invariance properties built by deep convolutional networks can be cast as a form of stable group invariance, enabling more abstract, powerful invariant representations.

Abstract

Many signal categories in vision and auditory problems are invariant to the action of transformation groups, such as translations, rotations or frequency transpositions. This property motivates the study of signal representations which are also invariant to the action of these transformation groups. For instance, translation invariance can be achieved with a registration or with auto-correlation measures.