Does training with blurred images bring convolutional neural networks closer to humans with respect to robust object recognition and internal representations?
It has been suggested that perceiving blurry images in addition to sharp images contributes to the development of robust human visual processing. To computationally investigate the effect of exposure to blurry images, we trained convolutional neural networks (CNNs) on ImageNet object recognition wit...
Main Authors: | Sou Yoshihara, Taiki Fukiage, Shin'ya Nishida |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-02-01
|
Series: | Frontiers in Psychology |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyg.2023.1047694/full |
Similar Items
-
Image Blur Classification and Unintentional Blur Removal
by: Rui Huang, et al.
Published: (2019-01-01) -
The Effect of Blurred Perceptual Training on the Decision Making of Skilled Football Referees
by: Tammie van Biemen, et al.
Published: (2018-09-01) -
Improving defocus blur measures using robust regularization
by: Usman Ali, et al.
Published: (2022-09-01) -
Using Blur for Perceptual Investigation and Training in Sport? A Clear Picture of the Evidence and Implications for Future Research
by: Annabelle Limballe, et al.
Published: (2022-03-01) -
AUTOMATIC IDENTIFICATION METHOD OF BLURRED IMAGES
by: Mikolaj Karpinski, et al.
Published: (2015-03-01)