Recurrent neural circuits for contour detection

2020/10/29 by Linsley, Drew, Kim, Junkyung, Ashok, Alekh +1 · 2 citations
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2010.15314

Abstract

We introduce a deep recurrent neural network architecture that approximates visual cortical circuits. We show that this architecture, which we refer to as the gamma-net, learns to solve contour detection tasks with better sample efficiency than state-of-the-art feedforward networks, while also exhibiting a classic perceptual illusion, known as the orientation-tilt illusion. Correcting this illusion significantly reduces gamma-net contour detection accuracy by driving it to prefer low-level edges over high-level object boundary contours. Overall, our study suggests that the orientation-tilt illusion is a byproduct of neural circuits that help biological visual systems achieve robust and efficient contour detection, and that incorporating these circuits in artificial neural networks can improve computer vision.

Cited by

• From Prediction to Understanding: Will AI Foundation Models Transform Brain Science?
• Incorporating Visual Cortical Lateral Connection Properties into CNN: Recurrent Activation and Excitatory-Inhibitory Separation

Related

• A biological vision inspired framework for machine perception of abutting grating illusory contours
• Predictive coding feedback results in perceived illusory contours in a recurrent neural network
• Convolutional Neural Networks Exploiting Attributes of Biological Neurons
• Visually-salient contour detection using a V1 neural model with horizontal connections
• Revealing Fine Structures of the Retinal Receptive Field by Deep Learning Networks