# Self-supervised learning through the eyes of a child

arXiv: https://arxiv.org/abs/2007.16189 · HTML: https://mlsanity.com/paper/2007.16189/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2020.

## Built on by (most cited first, 30 of 61)

- [A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends](https://mlsanity.com/paper/2301.05712/) (2023)
- [Partial success in closing the gap between human and machine vision](https://mlsanity.com/paper/2106.07411/) (2021)
- [What Artificial Neural Networks Can Tell Us About Human Language Acquisition](https://mlsanity.com/paper/2208.07998/) (2022)
- [Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video](https://mlsanity.com/paper/2310.08584/) (2023)
- [Neither hype nor gloom do DNNs justice](https://mlsanity.com/paper/2312.05355/) (2023)
- [Self-Supervised Representation Learning from Flow Equivariance](https://mlsanity.com/paper/2101.06553/) (2021)
- [Do Vision and Language Models Share Concepts? A Vector Space Alignment Study](https://mlsanity.com/paper/2302.06555/) (2023)
- [Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Works](https://mlsanity.com/paper/2211.08129/) (2022)
- [Learning high-level visual representations from a child's perspective without strong inductive biases](https://mlsanity.com/paper/2305.15372/) (2023)
- [Enabling On-Device Self-Supervised Contrastive Learning With Selective Data Contrast](https://mlsanity.com/paper/2106.03796/) (2021)
- [Self-supervised video pretraining yields robust and more human-aligned visual representations](https://mlsanity.com/paper/2210.06433/) (2022)
- [Enabling On-Device Large Language Model Personalization with Self-Supervised Data Selection and Synthesis](https://mlsanity.com/paper/2311.12275/) (2023)
- [MEWL: Few-shot multimodal word learning with referential uncertainty](https://mlsanity.com/paper/2306.00503/) (2023)
- [The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiences](https://mlsanity.com/paper/2406.10447/) (2024)
- [Time to augment self-supervised visual representation learning](https://mlsanity.com/paper/2207.13492/) (2022)
- [Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception](https://mlsanity.com/paper/2509.15333/) (2025)
- [On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentation](https://mlsanity.com/paper/2112.07173/) (2021)
- [JUWELS Booster -- A Supercomputer for Large-Scale AI Research](https://mlsanity.com/paper/2108.11976/) (2021)
- [A Developmentally-Inspired Examination of Shape versus Texture Bias in Machines](https://mlsanity.com/paper/2202.08340/) (2022)
- [Self-supervised visual learning from interactions with objects](https://mlsanity.com/paper/2407.06704/) (2024)
- [Better artificial intelligence does not mean better models of biology](https://mlsanity.com/paper/2504.16940/) (2025)
- [The developmental trajectory of object recognition robustness: children are like small adults but unlike big deep neural networks](https://mlsanity.com/paper/2205.10144/) (2022)
- [Measuring and modeling the motor system with machine learning](https://mlsanity.com/paper/2103.11775/) (2021)
- [The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image](https://mlsanity.com/paper/2112.00725/) (2021)
- [Palm up: Playing in the Latent Manifold for Unsupervised Pretraining](https://mlsanity.com/paper/2210.10913/) (2022)
- [Are Vision Transformers More Data Hungry Than Newborn Visual Systems?](https://mlsanity.com/paper/2312.02843/) (2023)
- [Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problems](https://mlsanity.com/paper/2307.07734/) (2023)
- [Self-supervised learning of video representations from a child's perspective](https://mlsanity.com/paper/2402.00300/) (2024)
- [Memory Storyboard: Leveraging Temporal Segmentation for Streaming Self-Supervised Learning from Egocentric Videos](https://mlsanity.com/paper/2501.12254/) (2025)
- [BabyVLM: Data-Efficient Pretraining of VLMs Inspired by Infant Learning](https://mlsanity.com/paper/2504.09426/) (2025)

## Abstract (arXiv)

Within months of birth, children develop meaningful expectations about the world around them. How much of this early knowledge can be explained through generic learning mechanisms applied to sensory data, and how much of it requires more substantive innate inductive biases? Addressing this fundamental question in its full generality is currently infeasible, but we can hope to make real progress in more narrowly defined domains, such as the development of high-level visual categories, thanks to improvements in data collecting technology and recent progress in deep learning. In this paper, our goal is precisely to achieve such progress by utilizing modern self-supervised deep learning methods and a recent longitudinal, egocentric video dataset recorded from the perspective of three young children (Sullivan et al., 2020). Our results demonstrate the emergence of powerful, high-level visual representations from developmentally realistic natural videos using generic self-supervised learning objectives.