Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Emergence of foveal image sampling from learning to attend in visual scenes
Brian Cheung, Eric Weiss, Bruno Olshausen
Nov 05, 2016 (modified: Mar 04, 2017)ICLR 2017 conference submissionreaders: everyone
Abstract:We describe a neural attention model with a learnable retinal sampling lattice. The model is trained on a visual search task requiring the classification of an object embedded in a visual scene amidst background distractors using the smallest number of fixations. We explore the tiling properties that emerge in the model's retinal sampling lattice after training. Specifically, we show that this lattice resembles the eccentricity dependent sampling lattice of the primate retina, with a high resolution region in the fovea surrounded by a low resolution periphery. Furthermore, we find conditions where these emergent properties are amplified or eliminated providing clues to their function.
TL;DR:We show a foveal sampling lattice similar to those observed in biology emerges from our model and task.
Keywords:Computer vision, Deep learning, Supervised Learning