Recurrent neural circuits for contour detection
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.
arXiv commentPublished in ICLR 2020
Cited by in corpus (6)
- Rethinking Interactive Image Segmentation: Feature Space Annotation
- Understanding the computational demands underlying visual reasoning
- Disentangling neural mechanisms for perceptual grouping
- Stable and expressive recurrent vision models
- Tracking Without Re-recognition in Humans and Machines
- The Challenge of Appearance-Free Object Tracking with Feedforward Neural Networks