Building a better probabilistic model of images by factorization

We describe a directed bilinear model that learns higherorder groupings among features of natural images. The model represents images in terms of two sets of latent variables: one set of variables represents which feature groups are active, while the other specifies the relative activity within groups. Such a factorized representation is beneficial because it is stable in response to small variations in the placement of features while still preserving information about relative spatial relationships. When trained on MNIST digits, the resulting representation provides state of the art performance in classification using a simple classifier. When trained on natural images, the model learns to group features according to proximity in position, orientation, and scale. The model achieves high log-likelihood (-94 nats), surpassing the current state of the art for natural images achievable with an mcRBM model. 1

• Type: Journal
• Year: 2011
• Where: ICCV
• Authors: Jack Culpepper, Jascha Sohl-Dickstein, Bruno Olahausen
• Keywords: Computer Vision, Feature Groups, ICCV 2011, Latent Variables, Log Likelihood