We investigate the geometric properties of the functions learned by trai...
We give a formal procedure for computing preimages of convolutional netw...
Discriminative latent variable models (LVM) are frequently applied to va...
This paper provides an extensive study on the availability of image
repr...
Supervised training of a convolutional network for object classification...
Evidence is mounting that Convolutional Networks (ConvNets) are the most...
Despite the success of the popular kernelized support vector machines, t...
Computer vision tasks are traditionally defined and evaluated using sema...