# Emergence of foveal image sampling from learning to attend in visual scenes

arXiv: https://arxiv.org/abs/1611.09430 · HTML: https://mlsanity.com/paper/1611.09430/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2016.

## Built on by (most cited first, 8 of 8)

- [Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop](https://mlsanity.com/paper/2506.10968/) (2025)
- [Foveation in the Era of Deep Learning](https://mlsanity.com/paper/2312.01450/) (2023)
- [Human Eyes Inspired Recurrent Neural Networks are More Robust Against Adversarial Noises](https://mlsanity.com/paper/2206.07282/) (2022)
- [What if Eye...? Computationally Recreating Vision Evolution](https://mlsanity.com/paper/2501.15001/) (2025)
- [FOVI: A biologically-inspired foveated interface for deep vision models](https://mlsanity.com/paper/2602.03766/) (2026)
- [URLOST: Unsupervised Representation Learning without Stationarity or Topology](https://mlsanity.com/paper/2310.04496/) (2023)
- [Foveation-based Deep Video Compression without Motion Search](https://mlsanity.com/paper/2203.16490/) (2022)
- [Task-driven Processing with Coarse-to-Fine Glimpse-based Active Perception](https://mlsanity.com/paper/2609.09025/) (2026)

## Abstract (arXiv)

We describe a neural attention model with a learnable retinal sampling lattice. The model is trained on a visual search task requiring the classification of an object embedded in a visual scene amidst background distractors using the smallest number of fixations. We explore the tiling properties that emerge in the model's retinal sampling lattice after training. Specifically, we show that this lattice resembles the eccentricity dependent sampling lattice of the primate retina, with a high resolution region in the fovea surrounded by a low resolution periphery. Furthermore, we find conditions where these emergent properties are amplified or eliminated providing clues to their function.