An image-computable model of human visual shape similarity
Fig 8
ShapeComp neural network for estimating a shape’s 22-Dimensional ShapeComp coordinates.
Neural networks in (A) MATLAB (MatNet) and (B) Python (KerNet1) were trained on 800,000 shapes to get as input the shape x,y coordinates and output the 22D high-dimensional shape space. (C) Kernet2, also in Python, was trained to output the ShapeComp coordinates from 40×40 image patches. (D) The networks 22-dimensional distances across all pairwise comparisons of 1000 untrained shapes are highly correlated to the pattern of distances from the original ShapeComp solution.