Unsupervised Learning of Group Invariant and Equivariant Representations

02/15/2022
by   Robin Winter, et al.
9

Equivariant neural networks, whose hidden features transform according to representations of a group G acting on the data, exhibit training efficiency and an improved generalisation performance. In this work, we extend group invariant and equivariant representation learning to the field of unsupervised deep learning. We propose a general learning strategy based on an encoder-decoder framework in which the latent representation is disentangled in an invariant term and an equivariant group action component. The key idea is that the network learns the group action on the data space and thus is able to solve the reconstruction task from an invariant data representation, hence avoiding the necessity of ad-hoc group-specific implementations. We derive the necessary conditions on the equivariant encoder, and we present a construction valid for any G, both discrete and continuous. We describe explicitly our construction for rotations, translations and permutations. We test the validity and the robustness of our approach in a variety of experiments with diverse data types employing different network architectures.

READ FULL TEXT
research
07/07/2022

Equivariant Representation Learning via Class-Pose Decomposition

We introduce a general method for learning representations that are equi...
research
09/06/2018

Unsupervised Learning of View-invariant Action Representations

The recent success in human action recognition with deep learning method...
research
09/29/2022

Equivariant maps from invariant functions

In equivariant machine learning the idea is to restrict the learning to ...
research
12/24/2014

Transformation Properties of Learned Visual Representations

When a three-dimensional object moves relative to an observer, a change ...
research
03/10/2021

On the primitivity of the AES key-schedule

The key-scheduling algorithm in the AES is the component responsible for...
research
12/11/2020

Unsupervised deep learning for individualized brain functional network identification

A novel unsupervised deep learning method is developed to identify indiv...
research
11/11/2020

Invariant Deep Compressible Covariance Pooling for Aerial Scene Categorization

Learning discriminative and invariant feature representation is the key ...

Please sign up or login with your details

Forgot password? Click here to reset