A solution to generalized learning from small training sets found in everyday infant experiences

• URL: http://arxiv.org/abs/2510.15060v1
• Date: Thu, 16 Oct 2025 18:21:55 GMT
• Title: A solution to generalized learning from small training sets found in everyday infant experiences
• Abstract summary: We analyze egocentric images from 14 infants (aged 7 to 11 months)<n>We show that their everyday visual input exhibits a lumpy similarity structure, with clusters of highly similar images interspersed with rarer, more variable ones.<n>Experiments show that mimicking this structure in machines improves generalization from small datasets in machine learning.
• Score: 6.323444741009534
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Young children readily recognize and generalize visual objects labeled by common nouns, suggesting that these basic level object categories may be given. Yet if they are, how they arise remains unclear. We propose that the answer lies in the statistics of infant daily life visual experiences. Whereas large and diverse datasets typically support robust learning and generalization in human and machine learning, infants achieve this generalization from limited experiences. We suggest that the resolution of this apparent contradiction lies in the visual diversity of daily life, repeated experiences with single object instances. Analyzing egocentric images from 14 infants (aged 7 to 11 months) we show that their everyday visual input exhibits a lumpy similarity structure, with clusters of highly similar images interspersed with rarer, more variable ones, across eight early-learned categories. Computational experiments show that mimicking this structure in machines improves generalization from small datasets in machine learning. The natural lumpiness of infant experience may thus support early category learning and generalization and, more broadly, offer principles for efficient learning across a variety of problems and kinds of learners.

Related papers

• Characterizing the visual representation of objects from the child's view [2.586100784625842]
  We analyzed first-person videos of young children's visual experience at home from the BabyView dataset.<n>We found that children's object category exposure was highly skewed.<n> Category exemplars were highly variable: children encountered objects from unusual angles, in highly cluttered scenes, and partially occluded views.
  arXiv  Detail & Related papers  (2026-05-14T15:52:20Z)
• Unique Lives, Shared World: Learning from Single-Life Videos [77.78726253186024]
  We leverage the multiple viewpoints naturally captured within a single life to learn a visual encoder in a self-supervised manner.<n>We show that models trained independently on different lives develop a highly aligned geometric understanding.<n>Third, we demonstrate that training on up to 30 hours from one week of the same person's life leads to comparable performance to training on 30 hours of diverse web data.
  arXiv  Detail & Related papers  (2025-12-03T18:59:57Z)
• Assessing the alignment between infants' visual and linguistic experience using multimodal language models [2.275358921334511]
  How aligned in time are children's visual and linguistic experiences during everyday learning?<n>We show that idealized aligned moments for learning are relatively rare in children's everyday experiences compared to modern machine learning datasets.<n>These findings suggest that infrequent alignment is a constraint for models describing early word learning.
  arXiv  Detail & Related papers  (2025-11-24T06:58:16Z)
• UNIFORM: Unifying Knowledge from Large-scale and Diverse Pre-trained Models [62.76435672183968]
  We introduce a novel framework, namely UNIFORM, for knowledge transfer from a diverse set of off-the-shelf models into one student model.<n>We propose a dedicated voting mechanism to capture the consensus of knowledge both at the logit level and at the feature level.<n>Experiments demonstrate that UNIFORM effectively enhances unsupervised object recognition performance compared to strong knowledge transfer baselines.
  arXiv  Detail & Related papers  (2025-08-27T00:56:11Z)
• Toddlers' Active Gaze Behavior Supports Self-Supervised Object Learning [4.612042044544857]
  We show that toddlers' gaze strategy supports the learning of invariant object representations.<n>Our work reveals how toddlers' gaze behavior may support their development of view-invariant object recognition.
  arXiv  Detail & Related papers  (2024-11-04T10:44:46Z)
• A model of early word acquisition based on realistic-scale audiovisual naming events [10.047470656294333]
  We studied the extent to which early words can be acquired through statistical learning from regularities in audiovisual sensory input. We simulated word learning in infants up to 12 months of age in a realistic setting, using a model that learns from statistical regularities in raw speech and pixel-level visual input. Results show that the model effectively learns to recognize words and associate them with corresponding visual objects, with a vocabulary growth rate comparable to that observed in infants.
  arXiv  Detail & Related papers  (2024-06-07T21:05:59Z)
• Self-supervised learning of video representations from a child's perspective [27.439294457852423]
  Children learn powerful internal models of the world around them from a few years of egocentric visual experience. Can such internal models be learned from a child's visual experience with highly generic learning algorithms or do they require strong inductive biases?
  arXiv  Detail & Related papers  (2024-02-01T03:27:26Z)
• Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Framework [83.21732533130846]
  The paper focuses on large in-the-wild databases, i.e., Aff-Wild and Aff-Wild2. It presents the design of two classes of deep neural networks trained with these databases. A novel multi-task and holistic framework is presented which is able to jointly learn and effectively generalize and perform affect recognition.
  arXiv  Detail & Related papers  (2021-03-29T17:36:20Z)
• Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types [50.1843146606122]
  A simple form of transfer learning is common in current state-of-the-art computer vision models. Previous systematic studies of transfer learning have been limited and the circumstances in which it is expected to work are not fully understood. In this paper we carry out an extensive experimental exploration of transfer learning across vastly different image domains.
  arXiv  Detail & Related papers  (2021-03-24T16:24:20Z)
• Evaluation of Complexity Measures for Deep Learning Generalization in Medical Image Analysis [77.34726150561087]
  PAC-Bayes flatness-based and path norm-based measures produce the most consistent explanation for the combination of models and data. We also investigate the use of multi-task classification and segmentation approach for breast images.
  arXiv  Detail & Related papers  (2021-03-04T20:58:22Z)
• What Can You Learn from Your Muscles? Learning Visual Representation from Human Interactions [50.435861435121915]
  We use human interaction and attention cues to investigate whether we can learn better representations compared to visual-only representations. Our experiments show that our "muscly-supervised" representation outperforms a visual-only state-of-the-art method MoCo.
  arXiv  Detail & Related papers  (2020-10-16T17:46:53Z)
• Learning abstract structure for drawing by efficient motor program induction [52.13961975752941]
  We develop a naturalistic drawing task to study how humans rapidly acquire structured prior knowledge. We show that people spontaneously learn abstract drawing procedures that support generalization. We propose a model of how learners can discover these reusable drawing programs.
  arXiv  Detail & Related papers  (2020-08-08T13:31:14Z)
• A Computational Model of Early Word Learning from the Infant's Point of View [15.443815646555125]
  The present study uses egocentric video and gaze data collected from infant learners during natural toy play with their parents. We then used a Convolutional Neural Network (CNN) model to process sensory data from the infant's point of view and learn name-object associations from scratch. As the first model that takes raw egocentric video to simulate infant word learning, the present study provides a proof of principle that the problem of early word learning can be solved.
  arXiv  Detail & Related papers  (2020-06-04T12:08:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.