Next Article in Journal
Partial Similarity Reveals Dynamics in Brainstem-Midbrain Networks during Trigeminal Nociception
Next Article in Special Issue
A Framework to Assess the Information Dynamics of Source EEG Activity and Its Application to Epileptic Brain Networks
Previous Article in Journal
Investigating Gait, Movement, and Coordination in Children with Neurodevelopmental Disorders: Is There a Role for Motor Abnormalities in Atypical Neurodevelopment?
Previous Article in Special Issue
Effects of Transcranial Electrical Stimulation on Human Auditory Processing and Behavior—A Review
Open AccessArticle

Study on Representation Invariances of CNNs and Human Visual Information Processing Based on Data Augmentation

Henan Key Laboratory of Imaging and Intelligent Processing, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, China
*
Author to whom correspondence should be addressed.
Brain Sci. 2020, 10(9), 602; https://doi.org/10.3390/brainsci10090602
Received: 29 June 2020 / Revised: 9 August 2020 / Accepted: 13 August 2020 / Published: 2 September 2020
(This article belongs to the Special Issue Human Brain Dynamics: Latest Advances and Prospects)
Representation invariance plays a significant role in the performance of deep convolutional neural networks (CNNs) and human visual information processing in various complicated image-based tasks. However, there has been abounding confusion concerning the representation invariance mechanisms of the two sophisticated systems. To investigate their relationship under common conditions, we proposed a representation invariance analysis approach based on data augmentation technology. Firstly, the original image library was expanded by data augmentation. The representation invariances of CNNs and the ventral visual stream were then studied by comparing the similarities of the corresponding layer features of CNNs and the prediction performance of visual encoding models based on functional magnetic resonance imaging (fMRI) before and after data augmentation. Our experimental results suggest that the architecture of CNNs, combinations of convolutional and fully-connected layers, developed representation invariance of CNNs. Remarkably, we found representation invariance belongs to all successive stages of the ventral visual stream. Hence, the internal correlation between CNNs and the human visual system in representation invariance was revealed. Our study promotes the advancement of invariant representation of computer vision and deeper comprehension of the representation invariance mechanism of human visual information processing. View Full-Text
Keywords: representation invariance; CNNs; human visual information processing; data augmentation; fMRI visual encoding model representation invariance; CNNs; human visual information processing; data augmentation; fMRI visual encoding model
Show Figures

Graphical abstract

MDPI and ACS Style

Cui, Y.; Zhang, C.; Qiao, K.; Wang, L.; Yan, B.; Tong, L. Study on Representation Invariances of CNNs and Human Visual Information Processing Based on Data Augmentation. Brain Sci. 2020, 10, 602.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop