# Learning Visual Features Under Motion Invariance

arXiv: https://arxiv.org/abs/1909.00350 · HTML: https://mlsanity.com/paper/1909.00350/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2019.

## Built on by (most cited first, 3 of 3)

- [Stochastic Coherence Over Attention Trajectory For Continuous Learning In Video Streams](https://mlsanity.com/paper/2204.12193/) (2022)
- [PARTIME: Scalable and Parallel Processing Over Time with Deep Neural Networks](https://mlsanity.com/paper/2210.09147/) (2022)
- [Nature-Inspired Local Propagation](https://mlsanity.com/paper/2402.05959/) (2024)

## Abstract (arXiv)

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.