AUTHOR=Yoshihara Sou , Fukiage Taiki , Nishida Shin'ya 

TITLE=Does training with blurred images bring convolutional neural networks closer to humans with respect to robust object recognition and internal representations?

JOURNAL=Frontiers in Psychology

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2023.1047694

DOI=10.3389/fpsyg.2023.1047694

ISSN=1664-1078

ABSTRACT=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 with a variety of combinations of sharp and blurred images. In agreement with recent reports, mixed training on sharp and blurred images (B+S) brings CNNs closer to humans with respect to robust object recognition against a change in image blur. B+S training also slightly reduces the texture bias of CNNs in recognition of shape-texture cue conflict images, but the effect is not strong enough to achieve human-level shape bias. Other tests also suggest that B+S training cannot produce robust human-like object recognition based on global configuration features. Using representational similarity analysis and zero-shot transfer learning, we also show that B+S-Net does not facilitate blur-robust object recognition through separate specialized sub-networks, one network for sharp images and another for blurry images, but through a single network analyzing image features common across sharp and blurry images. However, blur training alone does not automatically create a mechanism like the human brain in which sub-band information is integrated into a common representation. Our analyses suggest that exposure to blurred images helps the human brain develop neural networks that robustly recognize the surrounding world, but on its own cannot bridge the large gap separating humans and CNNs.