Retinotopic Mapping Enhances the Robustness of Convolutional Neural Networks

arXiv:2402.15480v1 Announce Type: new
Abstract: Foveated vision, a trait shared by many animals, including humans, has not been fully utilized in machine learning applications, despite its significant contributions to biological visual function. This study investigates whether retinotopic mapping, a critical component of foveated vision, can enhance image categorization and localization performance when integrated into deep convolutional neural networks (CNNs). Retinotopic mapping was integrated into the inputs of standard off-the-shelf convolutional neural networks (CNNs), which were then retrained on the ImageNet …

abstract animals applications arxiv convolutional neural networks cs.cv function humans image localization machine machine learning machine learning applications mapping networks neural networks performance q-bio.nc robustness study type vision visual