Learning Visual Features Under Motion Invariance

TL;DR

This paper introduces a novel theory for learning visual features from video streams based on motion invariance, enabling unsupervised, multi-layer feature extraction that aligns with biological vision and physics principles.

Contribution

It proposes a new variational framework for unsupervised learning of convolutional filters from motion-invariant visual streams, differing from traditional supervised CNNs.

Findings

Develops a variational principle-based theory for motion-invariant feature learning.

Provides a computational scheme for unsupervised multi-layer feature extraction.

Offers insights into biological vision and information-based learning principles.

Abstract

Humans are continuously exposed to a stream of visual data with a natural temporal structure. However, most successful computer vision algorithms work at image level, completely discarding the precious information carried by motion. In this paper, we claim that processing visual streams naturally leads to formulate the motion invariance principle, which enables the construction of a new theory of learning that originates from variational principles, just like in physics. Such principled approach is well suited for a discussion on a number of interesting questions that arise in vision, and it offers a well-posed computational scheme for the discovery of convolutional filters over the retina. Differently from traditional convolutional networks, which need massive supervision, the proposed theory offers a truly new scenario for the unsupervised processing of video signals, where features are extracted in a multi-layer architecture with motion invariance. While the theory enables the implementation of novel computer vision systems, it also sheds light on the role of information-based principles to drive possible biological solutions.