Cargando…
Which deep learning model can best explain object representations of within-category exemplars?
Deep neural network (DNN) models realize human-equivalent performance in tasks such as object recognition. Recent developments in the field have enabled testing the hierarchical similarity of object representation between the human brain and DNNs. However, the representational geometry of object exe...
Autor principal: | |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
The Association for Research in Vision and Ophthalmology
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8444465/ https://www.ncbi.nlm.nih.gov/pubmed/34520508 http://dx.doi.org/10.1167/jov.21.10.12 |
_version_ | 1784568497939939328 |
---|---|
author | Lee, Dongha |
author_facet | Lee, Dongha |
author_sort | Lee, Dongha |
collection | PubMed |
description | Deep neural network (DNN) models realize human-equivalent performance in tasks such as object recognition. Recent developments in the field have enabled testing the hierarchical similarity of object representation between the human brain and DNNs. However, the representational geometry of object exemplars within a single category using DNNs is unclear. In this study, we investigate which DNN model has the greatest ability to explain invariant within-category object representations by computing the similarity between representational geometries of visual features extracted at the high-level layers of different DNN models. We also test for the invariability of within-category object representations of these models by identifying object exemplars. Our results show that transfer learning models based on ResNet50 best explained both within-category object representation and object identification. These results suggest that the invariability of object representations in deep learning depends not on deepening the neural network but on building a better transfer learning model. |
format | Online Article Text |
id | pubmed-8444465 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | The Association for Research in Vision and Ophthalmology |
record_format | MEDLINE/PubMed |
spelling | pubmed-84444652021-09-30 Which deep learning model can best explain object representations of within-category exemplars? Lee, Dongha J Vis Special Issue Deep neural network (DNN) models realize human-equivalent performance in tasks such as object recognition. Recent developments in the field have enabled testing the hierarchical similarity of object representation between the human brain and DNNs. However, the representational geometry of object exemplars within a single category using DNNs is unclear. In this study, we investigate which DNN model has the greatest ability to explain invariant within-category object representations by computing the similarity between representational geometries of visual features extracted at the high-level layers of different DNN models. We also test for the invariability of within-category object representations of these models by identifying object exemplars. Our results show that transfer learning models based on ResNet50 best explained both within-category object representation and object identification. These results suggest that the invariability of object representations in deep learning depends not on deepening the neural network but on building a better transfer learning model. The Association for Research in Vision and Ophthalmology 2021-09-14 /pmc/articles/PMC8444465/ /pubmed/34520508 http://dx.doi.org/10.1167/jov.21.10.12 Text en Copyright 2021 The Authors https://creativecommons.org/licenses/by-nc-nd/4.0/This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. |
spellingShingle | Special Issue Lee, Dongha Which deep learning model can best explain object representations of within-category exemplars? |
title | Which deep learning model can best explain object representations of within-category exemplars? |
title_full | Which deep learning model can best explain object representations of within-category exemplars? |
title_fullStr | Which deep learning model can best explain object representations of within-category exemplars? |
title_full_unstemmed | Which deep learning model can best explain object representations of within-category exemplars? |
title_short | Which deep learning model can best explain object representations of within-category exemplars? |
title_sort | which deep learning model can best explain object representations of within-category exemplars? |
topic | Special Issue |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8444465/ https://www.ncbi.nlm.nih.gov/pubmed/34520508 http://dx.doi.org/10.1167/jov.21.10.12 |
work_keys_str_mv | AT leedongha whichdeeplearningmodelcanbestexplainobjectrepresentationsofwithincategoryexemplars |