mlsanityData to 7 Oct 2026

Self-supervised learning through the eyes of a child

arXiv 2007.16189 ↗First posted 31 Jul 2020cs.CV cs.LG cs.NEcited by 61

Not on the map. Why?

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.

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 14; 2023: 14; 2024: 8; 2025: 11; 2026: 4.

61 papers.

Sort:

By area:

  1. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 205
  2. 2021Partial success in closing the gap between human and machine visioncited by 185
  3. 2022What Artificial Neural Networks Can Tell Us About Human Language Acquisitioncited by 97
  4. 2023Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled videocited by 40
  5. 2023Neither hype nor gloom do DNNs justicecited by 40
  6. 2021Self-Supervised Representation Learning from Flow Equivariancecited by 28
  7. 2023Do Vision and Language Models Share Concepts? A Vector Space Alignment Studycited by 27
  8. 2022Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Workscited by 24
  9. 2023Learning high-level visual representations from a child's perspective without strong inductive biasescited by 22
  10. 2021Enabling On-Device Self-Supervised Contrastive Learning With Selective Data Contrastcited by 21
  11. 2022Self-supervised video pretraining yields robust and more human-aligned visual representationscited by 20
  12. 2023Enabling On-Device Large Language Model Personalization with Self-Supervised Data Selection and Synthesiscited by 20
38 more
  1. 2023MEWL: Few-shot multimodal word learning with referential uncertaintycited by 17
  2. 2022Time to augment self-supervised visual representation learningcited by 15
  3. 2024The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiencescited by 15
  4. 2025Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perceptioncited by 13
  5. 2021On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentationcited by 12
  6. 2021JUWELS Booster -- A Supercomputer for Large-Scale AI Researchcited by 10
  7. 2022A Developmentally-Inspired Examination of Shape versus Texture Bias in Machinescited by 10
  8. 2024Self-supervised visual learning from interactions with objectscited by 10
  9. 2025Better artificial intelligence does not mean better models of biologycited by 10
  10. 2022The developmental trajectory of object recognition robustness: children are like small adults but unlike big deep neural networkscited by 9
  11. 2021Measuring and modeling the motor system with machine learningcited by 7
  12. 2021The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Imagecited by 7
  13. 2022Palm up: Playing in the Latent Manifold for Unsupervised Pretrainingcited by 7
  14. 2023Are Vision Transformers More Data Hungry Than Newborn Visual Systems?cited by 7
  15. 2023Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problemscited by 6
  16. 2024Self-supervised learning of video representations from a child's perspectivecited by 6
  17. 2025Memory Storyboard: Leveraging Temporal Segmentation for Streaming Self-Supervised Learning from Egocentric Videoscited by 6
  18. 2025BabyVLM: Data-Efficient Pretraining of VLMs Inspired by Infant Learningcited by 6
  19. 2022Automatically Discovering Novel Visual Categories with Self-supervised Prototype Learningcited by 5
  20. 2023Caregiver Talk Shapes Toddler Vision: A Computational Study of Dyadic Playcited by 5
  21. 2024Learning Object Semantic Similarity with Self-Supervisioncited by 5
  22. 2021Online Unsupervised Learning of Visual Representations and Categoriescited by 4
  23. 2021How much human-like visual experience do current self-supervised learning algorithms need in order to achieve human-level object recognition?cited by 4
  24. 2022Building Human-like Communicative Intelligence: A Grounded Perspectivecited by 4
  25. 2023A Computational Account Of Self-Supervised Visual Learning From Egocentric Object Playcited by 4
  26. 2024From Prototypes to General Distributions: An Efficient Curriculum for Masked Image Modelingcited by 4
  27. 2025On the robustness of modeling grounded word learning through a child's egocentric inputcited by 4
  28. 2022Improving generalization by mimicking the human visual dietcited by 2
  29. 2022Predicting Word Learning in Children from the Performance of Computer Vision Systemscited by 2
  30. 2023MIMo: A Multi-Modal Infant Model for Studying Cognitive Developmentcited by 2
  31. 2025Discovering Hidden Visual Concepts Beyond Linguistic Input in Infant Learningcited by 2
  32. 2025Learning to See Through a Baby's Eyes: Early Visual Diets Enable Robust Visual Intelligence in Humans and Machinescited by 2
  33. 2021Reverse-engineer the Distributional Structure of Infant Egocentric Views for Training Generalizable Image Classifierscited by 1
  34. 2022Predictive Event Segmentation and Representation with Neural Networks: A Self-Supervised Model Assessed by Psychological Experimentscited by 1
  35. 2023Beyond the limitations of any imaginable mechanism: large language models and psycholinguisticscited by 1
  36. 2025Human Gaze Boosts Object-Centered Representation Learningcited by 1
  37. 2025Unsupervised Acquisition of Discrete Grammatical Categoriescited by 1
  38. 2022Embodied vision for learning object representationscited by 0

50 most cited of 61 All 61 (JSON)