# Discovering Hidden Visual Concepts Beyond Linguistic Input in Infant Learning

Source: [Discovering Hidden Visual Concepts Beyond Linguistic Input in Infant Learning](<https://www.sota2.com/research/paper/68fa79581e209131cea7d310>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-02T10:30:07.948Z

Authors: Xueyi Ke, Satoshi Tsutsui, Yayun Zhang, Bihan Wen

Published: 2025-01-09T12:55:55.000Z

## Abstract

Infants develop complex visual understanding rapidly, even preceding the acquisition of linguistic skills. As computer vision seeks to replicate the human vision system, understanding infant visual development may offer valuable insights. In this paper, we present an interdisciplinary study exploring this question: can a computational model that imitates the infant learning process develop broader visual concepts that extend beyond the vocabulary it has heard, similar to how infants naturally learn? To investigate this, we analyze a recently published model in Science by Vong et al., which is trained on longitudinal, egocentric images of a single child paired with transcribed parental speech. We perform neuron labeling to identify visual concept neurons hidden in the model's internal representations. We then demonstrate that these neurons can recognize objects beyond the model's original vocabulary. Furthermore, we compare the differences in representation between infant models and those in modern computer vision models, such as CLIP and ImageNet pre-trained model. Ultimately, our work bridges cognitive science and computer vision by analyzing the internal representations of a computational model trained on an infant visual and linguistic inputs. Project page is available at https://kexueyi.github.io/webpage-discover-hidden-visual-concepts.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2501.05205>)

[PDF](<https://arxiv.org/pdf/2501.05205.pdf>)

[Implementation](<https://kexueyi.github.io/webpage-discover-hidden-visual-concepts>)
