# Simulated Cortical Magnification Supports Self-Supervised Object Learning

arXiv: https://arxiv.org/abs/2509.15751 · HTML: https://mlsanity.com/paper/2509.15751/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 19 Sep 2025.

## Builds on (most cited first, 13 of 13)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [CORe50: a New Dataset and Benchmark for Continuous Object Recognition](https://mlsanity.com/paper/1705.03550/) (2017)
- [Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex](https://mlsanity.com/paper/1604.03640/) (2016)
- [Learning high-level visual representations from a child's perspective without strong inductive biases](https://mlsanity.com/paper/2305.15372/) (2023)
- [Self-supervised video pretraining yields robust and more human-aligned visual representations](https://mlsanity.com/paper/2210.06433/) (2022)
- [Time to augment self-supervised visual representation learning](https://mlsanity.com/paper/2207.13492/) (2022)
- [On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentation](https://mlsanity.com/paper/2112.07173/) (2021)
- [Self-supervised visual learning from interactions with objects](https://mlsanity.com/paper/2407.06704/) (2024)
- [Caregiver Talk Shapes Toddler Vision: A Computational Study of Dyadic Play](https://mlsanity.com/paper/2312.04118/) (2023)
- [Learning Object Semantic Similarity with Self-Supervision](https://mlsanity.com/paper/2405.05143/) (2024)
- [Human Gaze Boosts Object-Centered Representation Learning](https://mlsanity.com/paper/2501.02966/) (2025)

## Abstract (arXiv)

Recent self-supervised learning models simulate the development of semantic object representations by training on visual experience similar to that of toddlers. However, these models ignore the foveated nature of human vision with high/low resolution in the center/periphery of the visual field. Here, we investigate the role of this varying resolution in the development of object representations. We leverage two datasets of egocentric videos that capture the visual experience of humans during interactions with objects. We apply models of human foveation and cortical magnification to modify these inputs, such that the visual content becomes less distinct towards the periphery. The resulting sequences are used to train two bio-inspired self-supervised learning models that implement a time-based learning objective. Our results show that modeling aspects of foveated vision improves the quality of the learned object representations in this setting. Our analysis suggests that this improvement comes from making objects appear bigger and inducing a better trade-off between central and peripheral visual information. Overall, this work takes a step towards making models of humans' learning of visual representations more realistic and performant.