HyperNets and their application to learning spatial transformations

TL;DR

This paper introduces HyperNets, a higher-order neural network framework capable of learning and generalizing spatial transformations like rotation and affine changes, and normalizing images to canonical forms.

Contribution

The paper presents HyperNets, a novel higher-order neural network framework designed to learn and generalize spatial transformations such as rotation and affine transformations.

Findings

HyperNets can learn to generalize spatial transformations.

They can normalize images to canonical forms.

The framework effectively handles rotation and affine transformations.

Abstract

In this paper we propose a conceptual framework for higher-order artificial neural networks. The idea of higher-order networks arises naturally when a model is required to learn some group of transformations, every element of which is well-approximated by a traditional feedforward network. Thus the group as a whole can be represented as a hyper network. One of typical examples of such groups is spatial transformations. We show that the proposed framework, which we call HyperNets, is able to deal with at least two basic spatial transformations of images: rotation and affine transformation. We show that HyperNets are able not only to generalize rotation and affine transformation, but also to compensate the rotation of images bringing them into canonical forms.