Using retinotopic mapping in convolutional neural networks for object categorization leads to saliency-based visual object localization
Jean-Nicolas Jérémie, Emmanuel Dauce, Laurent Perrinet · FENS Forum 2024
This study investigates whether retinotopic mapping can be integrated into classical computational architectures that model biological visual pathways, specifically deep convolutional neural networks (dCNNs), to enhance image categorization and localization performance. The study retrains a retinotopic dCNN on the ImageNet task, which involves classifying images into 1000 labels.The study's primary finding is that standard deep CNNs are highly effective in processing retinotopic inputs, despite the significant transformation of visual inputs that this mapping entails (A). The ResNet101 network
ePoster · Neuroscience