# Learning Image Relations with Contrast Association Networks

## TL;DR

This paper introduces Contrast Association Units (CAUs), a neural network module designed to explicitly model relations between image pairs, improving the learning of fundamental image transformations.

## Contribution

It proposes a novel neural network module, CAU, with a specialized learning algorithm, enhancing relation inference in image tasks compared to traditional methods.

## Key findings

- CAUs outperform conventional neural networks in learning image transformations
- The multiplicative update algorithm effectively trains CAUs due to non-negative weights
- Experiments demonstrate improved relation modeling in computer vision tasks

## Abstract

Inferring the relations between two images is an important class of tasks in computer vision. Examples of such tasks include computing optical flow and stereo disparity. We treat the relation inference tasks as a machine learning problem and tackle it with neural networks. A key to the problem is learning a representation of relations. We propose a new neural network module, contrast association unit (CAU), which explicitly models the relations between two sets of input variables. Due to the non-negativity of the weights in CAU, we adopt a multiplicative update algorithm for learning these weights. Experiments show that neural networks with CAUs are more effective in learning five fundamental image transformations than conventional neural networks.