A polar prediction model for learning to represent visual transformations

TL;DR

This paper introduces a polar prediction model for visual transformations that leverages Fourier principles and group theory to improve temporal prediction in videos, offering interpretability and biological relevance.

Contribution

It proposes a novel polar architecture for self-supervised learning of visual transformations, grounded in Fourier shift theorem, achieving better prediction and biological plausibility.

Findings

Outperforms traditional motion compensation in prediction accuracy

Rivals conventional deep networks in prediction performance

Resembles primate V1 neuron models in computation structure

Abstract

All organisms make temporal predictions, and their evolutionary fitness level depends on the accuracy of these predictions. In the context of visual perception, the motions of both the observer and objects in the scene structure the dynamics of sensory signals, allowing for partial prediction of future signals based on past ones. Here, we propose a self-supervised representation-learning framework that extracts and exploits the regularities of natural videos to compute accurate predictions. We motivate the polar architecture by appealing to the Fourier shift theorem and its group-theoretic generalization, and we optimize its parameters on next-frame prediction. Through controlled experiments, we demonstrate that this approach can discover the representation of simple transformation groups acting in data. When trained on natural video datasets, our framework achieves better prediction performance than traditional motion compensation and rivals conventional deep networks, while maintaining interpretability and speed. Furthermore, the polar computations can be restructured into components resembling normalized simple and direction-selective complex cell models of primate V1 neurons. Thus, polar prediction offers a principled framework for understanding how the visual system represents sensory inputs in a form that simplifies temporal prediction.