# Emergent Properties of Foveated Perceptual Systems

arXiv: https://arxiv.org/abs/2006.07991 · HTML: https://mlsanity.com/paper/2006.07991/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2020.

## Built on by (most cited first, 24 of 24)

- [Harmonizing the object recognition strategies of deep neural networks with humans](https://mlsanity.com/paper/2211.04533/) (2022)
- [FoveaTer: Foveated Transformer for Image Classification](https://mlsanity.com/paper/2105.14173/) (2021)
- [PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution](https://mlsanity.com/paper/2403.07589/) (2024)
- [Peripheral Vision Transformer](https://mlsanity.com/paper/2206.06801/) (2022)
- [Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop](https://mlsanity.com/paper/2506.10968/) (2025)
- [On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentation](https://mlsanity.com/paper/2112.07173/) (2021)
- [Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks](https://mlsanity.com/paper/2202.00838/) (2022)
- [Look, Focus, Act: Efficient and Robust Robot Learning via Human Gaze and Foveated Vision Transformers](https://mlsanity.com/paper/2507.15833/) (2025)
- [Passive Attention in Artificial Neural Networks Predicts Human Visual Selectivity](https://mlsanity.com/paper/2107.07013/) (2021)
- [LLMind: Bio-inspired Training-free Adaptive Visual Representations for Vision-Language Models](https://mlsanity.com/paper/2603.14882/) (2026)
- [Training on Foveated Images Improves Robustness to Adversarial Attacks](https://mlsanity.com/paper/2308.00854/) (2023)
- [Human Eyes Inspired Recurrent Neural Networks are More Robust Against Adversarial Noises](https://mlsanity.com/paper/2206.07282/) (2022)
- [Human Vision Based 3D Point Cloud Semantic Segmentation of Large-Scale Outdoor Scene](https://mlsanity.com/paper/2301.12972/) (2023)
- [Towards Two-Stream Foveation-based Active Vision Learning](https://mlsanity.com/paper/2403.15977/) (2024)
- [FOVI: A biologically-inspired foveated interface for deep vision models](https://mlsanity.com/paper/2602.03766/) (2026)
- [The Effects of Image Distribution and Task on Adversarial Robustness](https://mlsanity.com/paper/2102.10534/) (2021)
- [FovEx: Human-Inspired Explanations for Vision Transformers and Convolutional Neural Networks](https://mlsanity.com/paper/2408.02123/) (2024)
- [A Framework for Generating Semantically Ambiguous Images to Probe Human and Machine Perception](https://mlsanity.com/paper/2603.24730/) (2026)
- [How to augment your ViTs? Consistency loss and StyleAug, a random style transfer augmentation](https://mlsanity.com/paper/2112.09260/) (2021)
- [Temporal Slowness in Central Vision Drives Semantic Object Learning](https://mlsanity.com/paper/2602.04462/) (2026)
- [Foveation-Guided Dynamic Token Selection for Robust and Efficient Vision Transformers](https://mlsanity.com/paper/2607.09480/) (2026)
- [Matched Outcomes, Divergent Gaze: How Foveated MLLMs Search Compared to Humans](https://mlsanity.com/paper/2608.16514/) (2026)
- [FAVE: Foveated Adaptive Visual Encoding for Efficient Fine-Grained Visual Understanding](https://mlsanity.com/paper/2609.04392/) (2026)
- [Adaptive Observation Control for Active Visual Recognition](https://mlsanity.com/paper/2610.19624/) (2026)

## Abstract (arXiv)

The goal of this work is to characterize the representational impact that foveation operations have for machine vision systems, inspired by the foveated human visual system, which has higher acuity at the center of gaze and texture-like encoding in the periphery. To do so, we introduce models consisting of a first-stage textitfixed image transform followed by a second-stage textitlearnable convolutional neural network, and we varied the first stage component. The primary model has a foveated-textural input stage, which we compare to a model with foveated-blurred input and a model with spatially-uniform blurred input (both matched for perceptual compression), and a final reference model with minimal input-based compression. We find that: 1) the foveated-texture model shows similar scene classification accuracy as the reference model despite its compressed input, with greater i.i.d. generalization than the other models; 2) the foveated-texture model has greater sensitivity to high-spatial frequency information and greater robustness to occlusion, w.r.t the comparison models; 3) both the foveated systems, show a stronger center image-bias relative to the spatially-uniform systems even with a weight sharing constraint. Critically, these results are preserved over different classical CNN architectures throughout their learning dynamics. Altogether, this suggests that foveation with peripheral texture-based computations yields an efficient, distinct, and robust representational format of scene information, and provides symbiotic computational insight into the representational consequences that texture-based peripheral encoding may have for processing in the human visual system, while also potentially inspiring the next generation of computer vision models via spatially-adaptive computation. Code + Data available here: https://github.com/ArturoDeza/EmergentProperties