Deep Learning Neural Networks as a Model of Saccadic Generation

2021.

Krasovskaya S., Zhulikov G., MacInnes W.

Approximately twenty years ago, Laurent Itti and Christof Koch created a model of saliency in visual attention in an attempt to recreate the work of biological pyramidal neurons by mimicking neurons with centre-surround receptive fields. The Saliency Model has launched many studies that contributed to the understanding of layers of vision and the sphere of visual attention. The aim of the current study is to improve this model by using an artificial neural network as the spatial component of a model that generates saccades similar to how humans make saccadic eye movements. The proposed model uses a Leaky Integrate-and-Fire layer for temporal predictions, and replaces parallel feature maps with a deep learning neural network in order to create a generative model that is precise for both spatial and temporal shifts of attention. Our model was able to predict eye movements based on unsupervised learning from raw image input, combined with supervised learning from fixation maps retrieved during an eye-tracking experiment. The results imply that it is possible to match the spatial and temporal distributions of the model to spatial and temporal human distributions.

Keywords: зрительное внимание, visual attention, импульсные нейроны с утечкой, модели заметности, Itti and Koch, Итти и Кох, saliency models, models of salience, leaky integrate-and-fire neurons, saccadic generation, deep learning neural nets, Нейронные сети глубинного обучения, генерация саккад

Publication based on the results of: Interdisciplinary Studies of Vision (2019)