Search Results for author:
Found 4 papers, 0 papers with code
Teaching Compositionality to CNNs
Convolutional neural networks (CNNs) have shown great success in computer vision, approaching human-level performance when trained for specific tasks via application-specific loss functions.
Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data
We demonstrate that a generative model for object shapes can achieve state of the art results on challenging scene text recognition tasks, and with orders of magnitude fewer training images than required for competing discriminative methods.
A backward pass through a CNN using a generative model of its activations
Neural networks have shown to be a practical way of building a very complex mapping between a pre-specified input space and output space.
Hierarchical compositional feature learning
We introduce the hierarchical compositional network (HCN), a directed generative model able to discover and disentangle, without supervision, the building blocks of a set of binary images.
