2020/10/29 by Drew Linsley, Junkyung Kim, Linsley, Drew +7 · 3 citations
Chemistry · Computer Science · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Spectroscopy and Chemometric Analyses #cs.AI #cs.CV
paper · pdf · doi:10.48550/arxiv.2010.15314
Published in ICLR 2020
arxiv created 2020/10/29 · openalex publication_date 2020/10/29 · arxiv updated 2020/10/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31
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.