Recurrent neural circuits for contour detection
This addresses contour detection in computer vision, offering a biologically-inspired approach that is incremental but provides specific gains.
The authors tackled contour detection by introducing a recurrent neural network architecture called gamma-net that approximates visual cortical circuits, showing it learns with better sample efficiency than state-of-the-art feedforward networks and exhibits the orientation-tilt illusion, which when corrected reduces its accuracy.
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.