A. Akbarinia

Exploring the Categorical Nature of Colour Perception: Insights from Deep Networks

This study examines categorical colour perception using deep networks, showing alignment with human data and revealing the influence of both visual signals and linguistic factors.

Contrast Sensitivity Function in Deep Networks

This study examines the contrast sensitivity function (CSF) in deep neural networks, finding that human-like CSF characteristics emerge across different network architectures and tasks.

Emergent Color Categorization in a Neural Network trained for Object Recognition

This study shows that a CNN trained for object recognition develops categorical color perception, with clear borders between new colors that are invariant to training colors.