papers AI Learner
The Github is limit! Click to go to the new site.

Learning V1 cells with vector representations of local contents and matrix representations of local motions

2019-05-25
Ruiqi Gao, Jianwen Xie, Song-Chun Zhu, Ying Nian Wu

Abstract

Simple cells in primary visual cortex (V1) can be approximated by Gabor filters, and adjacent simple cells tend to have quadrature phase relationship. This paper entertains the hypothesis that a key purpose of such simple cells is to perceive local motions, i.e., displacements of pixels, caused by the relative motions between the agent and the surrounding environment. Specifically, we propose a representational model that couples the vector representations of local image contents with the matrix representations of local pixel displacements. When the image changes from one time frame to the next due to pixel displacements, the vector at each pixel is rotated by a matrix that represents the displacement of this pixel. We show that by learning from pair of images that are deformed versions of each other, we can learn both vector and matrix representations. The units in the learned vector representations reproduce properties of V1 simple cells. The learned model enables perceptual inference of local motions.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1902.03871

PDF

http://arxiv.org/pdf/1902.03871


Similar Posts

Comments