ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Qualitative similarities and differences in visual object representations between brains and deep networks

Jacob, G and Pramod, RT and Katti, H and Arun, SP (2021) Qualitative similarities and differences in visual object representations between brains and deep networks. In: Nature Communications, 12 (1).

nat_com_12-1_2021.pdf - Published Version

Download (1MB) | Preview
Spinselective-correlation-experiment-for-measurement-of-longrange-J-couplings-and-for-assignment-of-RS-enantiomers-from-the-residual-dipolar-couplings-and-DFTJournal-of-Physical-Chemistry-B.pdf - Published Supplemental Material

Download (3MB) | Preview
Official URL: https://doi.org/10.1038/s41467-021-22078-3


Deep neural networks have revolutionized computer vision, and their object representations across layers match coarsely with visual cortical areas in the brain. However, whether these representations exhibit qualitative patterns seen in human perception or brain representations remains unresolved. Here, we recast well-known perceptual and neural phenomena in terms of distance comparisons, and ask whether they are present in feedforward deep neural networks trained for object recognition. Some phenomena were present in randomly initialized networks, such as the global advantage effect, sparseness, and relative size. Many others were present after object recognition training, such as the Thatcher effect, mirror confusion, Weber�s law, relative size, multiple object normalization and correlated sparseness. Yet other phenomena were absent in trained networks, such as 3D shape processing, surface invariance, occlusion, natural parts and the global advantage. These findings indicate sufficient conditions for the emergence of these phenomena in brains and deep networks, and offer clues to the properties that could be incorporated to improve deep networks. © 2021, The Author(s).

Item Type: Journal Article
Publication: Nature Communications
Publisher: Nature Research
Additional Information: This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.
Department/Centre: Division of Biological Sciences > Centre for Neuroscience
Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited: 02 Jul 2021 16:04
Last Modified: 02 Jul 2021 16:04
URI: http://eprints.iisc.ac.in/id/eprint/68699

Actions (login required)

View Item View Item