Cargando…
Early experience with low-pass filtered images facilitates visual category learning in a neural network model
Humans are born with very low contrast sensitivity, meaning that inputs to the infant visual system are both blurry and low contrast. Is this solely a byproduct of maturational processes or is there a functional advantage for beginning life with poor visual acuity? We addressed the impact of poor vi...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9821476/ https://www.ncbi.nlm.nih.gov/pubmed/36608003 http://dx.doi.org/10.1371/journal.pone.0280145 |
_version_ | 1784865706106421248 |
---|---|
author | Jinsi, Omisa Henderson, Margaret M. Tarr, Michael J. |
author_facet | Jinsi, Omisa Henderson, Margaret M. Tarr, Michael J. |
author_sort | Jinsi, Omisa |
collection | PubMed |
description | Humans are born with very low contrast sensitivity, meaning that inputs to the infant visual system are both blurry and low contrast. Is this solely a byproduct of maturational processes or is there a functional advantage for beginning life with poor visual acuity? We addressed the impact of poor vision during early learning by exploring whether reduced visual acuity facilitated the acquisition of basic-level categories in a convolutional neural network model (CNN), as well as whether any such benefit transferred to subordinate-level category learning. Using the ecoset dataset to simulate basic-level category learning, we manipulated model training curricula along three dimensions: presence of blurred inputs early in training, rate of blur reduction over time, and grayscale versus color inputs. First, a training regime where blur was initially high and was gradually reduced over time—as in human development—improved basic-level categorization performance in a CNN relative to a regime in which non-blurred inputs were used throughout training. Second, when basic-level models were fine-tuned on a task including both basic-level and subordinate-level categories (using the ImageNet dataset), models initially trained with blurred inputs showed a greater performance benefit as compared to models trained exclusively on non-blurred inputs, suggesting that the benefit of blurring generalized from basic-level to subordinate-level categorization. Third, analogous to the low sensitivity to color that infants experience during the first 4–6 months of development, these advantages were observed only when grayscale images were used as inputs. We conclude that poor visual acuity in human newborns may confer functional advantages, including, as demonstrated here, more rapid and accurate acquisition of visual object categories at multiple levels. |
format | Online Article Text |
id | pubmed-9821476 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-98214762023-01-07 Early experience with low-pass filtered images facilitates visual category learning in a neural network model Jinsi, Omisa Henderson, Margaret M. Tarr, Michael J. PLoS One Research Article Humans are born with very low contrast sensitivity, meaning that inputs to the infant visual system are both blurry and low contrast. Is this solely a byproduct of maturational processes or is there a functional advantage for beginning life with poor visual acuity? We addressed the impact of poor vision during early learning by exploring whether reduced visual acuity facilitated the acquisition of basic-level categories in a convolutional neural network model (CNN), as well as whether any such benefit transferred to subordinate-level category learning. Using the ecoset dataset to simulate basic-level category learning, we manipulated model training curricula along three dimensions: presence of blurred inputs early in training, rate of blur reduction over time, and grayscale versus color inputs. First, a training regime where blur was initially high and was gradually reduced over time—as in human development—improved basic-level categorization performance in a CNN relative to a regime in which non-blurred inputs were used throughout training. Second, when basic-level models were fine-tuned on a task including both basic-level and subordinate-level categories (using the ImageNet dataset), models initially trained with blurred inputs showed a greater performance benefit as compared to models trained exclusively on non-blurred inputs, suggesting that the benefit of blurring generalized from basic-level to subordinate-level categorization. Third, analogous to the low sensitivity to color that infants experience during the first 4–6 months of development, these advantages were observed only when grayscale images were used as inputs. We conclude that poor visual acuity in human newborns may confer functional advantages, including, as demonstrated here, more rapid and accurate acquisition of visual object categories at multiple levels. Public Library of Science 2023-01-06 /pmc/articles/PMC9821476/ /pubmed/36608003 http://dx.doi.org/10.1371/journal.pone.0280145 Text en © 2023 Jinsi et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Jinsi, Omisa Henderson, Margaret M. Tarr, Michael J. Early experience with low-pass filtered images facilitates visual category learning in a neural network model |
title | Early experience with low-pass filtered images facilitates visual category learning in a neural network model |
title_full | Early experience with low-pass filtered images facilitates visual category learning in a neural network model |
title_fullStr | Early experience with low-pass filtered images facilitates visual category learning in a neural network model |
title_full_unstemmed | Early experience with low-pass filtered images facilitates visual category learning in a neural network model |
title_short | Early experience with low-pass filtered images facilitates visual category learning in a neural network model |
title_sort | early experience with low-pass filtered images facilitates visual category learning in a neural network model |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9821476/ https://www.ncbi.nlm.nih.gov/pubmed/36608003 http://dx.doi.org/10.1371/journal.pone.0280145 |
work_keys_str_mv | AT jinsiomisa earlyexperiencewithlowpassfilteredimagesfacilitatesvisualcategorylearninginaneuralnetworkmodel AT hendersonmargaretm earlyexperiencewithlowpassfilteredimagesfacilitatesvisualcategorylearninginaneuralnetworkmodel AT tarrmichaelj earlyexperiencewithlowpassfilteredimagesfacilitatesvisualcategorylearninginaneuralnetworkmodel |