CVSep 28, 2015

Learning FRAME Models Using CNN Filters

arXiv:1509.08379v366 citations
Originality Synthesis-oriented
AI Analysis

This is an incremental conceptual study for computer vision researchers exploring generative perspectives of CNNs.

The paper tackles the problem of generating realistic object and texture patterns by learning generative FRAME models using pre-learned CNN filters, resulting in the ability to create new CNN units and layers with an EM interpretation.

The convolutional neural network (ConvNet or CNN) has proven to be very successful in many tasks such as those in computer vision. In this conceptual paper, we study the generative perspective of the discriminative CNN. In particular, we propose to learn the generative FRAME (Filters, Random field, And Maximum Entropy) model using the highly expressive filters pre-learned by the CNN at the convolutional layers. We show that the learning algorithm can generate realistic and rich object and texture patterns in natural scenes. We explain that each learned model corresponds to a new CNN unit at a layer above the layer of filters employed by the model. We further show that it is possible to learn a new layer of CNN units using a generative CNN model, which is a product of experts model, and the learning algorithm admits an EM interpretation with binary latent variables.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes