Which deep learning model can best explain object representations of within-category exemplars?
- Authors
- Lee, Dongha
- Issue Date
- Sep-2021
- Publisher
- ASSOC RESEARCH VISION OPHTHALMOLOGY INC
- Keywords
- invariant object representations; deep neural networks; object exemplars; representation similarity; identification accuracy
- Citation
- JOURNAL OF VISION, v.21, no.10
- Journal Title
- JOURNAL OF VISION
- Volume
- 21
- Number
- 10
- URI
- http://scholarworks.bwise.kr/kbri/handle/2023.sw.kbri/299
- DOI
- 10.1167/jov.21.10.12
- ISSN
- 1534-7362
- Abstract
- 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.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - 연구본부 > 인지과학 연구그룹 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=http://scholarworks.bwise.kr/kbri/handle/2023.sw.kbri/299)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.