mlsanityData to 14 Oct 2026

A solution to generalized learning from small training sets found in infants repeated visual experiences of individual objects

arXiv 2510.15060 ↗First posted 16 Oct 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

One-year-old infants rapidly form and generalize categories from idiosyncratic experiences of very few exemplars of those categories. Here we provide evidence on the statistics of infants daily-life visual experiences for 8 object categories. Using a corpus of infant head-camera images recorded at mealtimes (87 mealtimes,14 infants), we measure the frequency of the unique instances of each category and the variability of the visual experiences within and across instances of the same category. The frequency distributions of instances for individual infants are highly skewed, containing many images of the same few objects along with fewer images of other instances. Graph theoretic measures of individual category experiences for individual children reveal a lumpy mix of high similarity and high variability, organized into multiple but interconnected clusters of high-similarity images. In computational experiments, we show that artificially created training sets characterized by an interconnected mix of high and low similarity support generalization to novel instances after limited training. We discuss implications for category recognition, and for learning more generally, by both humans and machines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 144 references that are in the map. First posted on arXiv 16 Oct 2025.

Builds on

34 of 144 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  6. 2020Scaling Laws for Neural Language Modelscited by 6,586
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  8. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  9. 2020Supervised Contrastive Learningcited by 2,829
  10. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  11. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 919
  12. 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 454
22 more
  1. 2021Explaining Neural Scaling Lawscited by 363
  2. 2023DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Datacited by 337
  3. 2025Perception Encoder: The best visual embeddings are not at the output of the networkcited by 326
  4. 2022Data Distributional Properties Drive Emergent In-Context Learning in Transformerscited by 309
  5. 2022TinyViT: Fast Pretraining Distillation for Small Vision Transformerscited by 234
  6. 2023SCLIP: Rethinking Self-Attention for Dense Vision-Language Inferencecited by 170
  7. 2022A Comprehensive Survey of Image Augmentation Techniques for Deep Learningcited by 97
  8. 2022The Effects of Regularization and Data Augmentation are Class Dependentcited by 67
  9. 2013Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robotscited by 58
  10. 2022Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networkscited by 55
  11. 2025Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inferencecited by 53
  12. 2021Nondeterminism and Instability in Neural Network Optimizationcited by 48
  13. 2019On Model Stability as a Function of Random Seedcited by 31
  14. 2025The emergence of sparse attention: impact of data distribution and benefits of repetitioncited by 25
  15. 2024Impacts of floating-point non-associativity on reproducibility for HPC and deep learning applicationscited by 24
  16. 2015Amodal Completion and Size Constancy in Natural Scenescited by 21
  17. 2022Image Amodal Completion: A Surveycited by 18
  18. 2018Deep Convolutional Neural Networks in the Face of Caricature: Identity and Image Revealedcited by 16
  19. 2024PetFace: A Large-Scale Dataset and Benchmark for Animal Identificationcited by 16
  20. 2024Pose-Aware Self-Supervised Learning with Viewpoint Trajectory Regularizationcited by 7
  21. 2025Attributes Shape the Embedding Space of Face Recognition Modelscited by 4
  22. 2015Understanding the Heavy Tailed Dynamics in Human Behaviorcited by 1

Built on by

Not cited yet.