Towards deep compositional networks
Authors:
- 1 December 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3470-3475
Abstract
Hierarchical feature learning based on convolutional neural networks (CNN) has recently shown significant potential in various computer vision tasks. While allowing high-quality discriminative feature learning, the downside of CNNs is the lack of explicit structure in features, which often leads to overfitting, absence of reconstruction from partial observations and limited generative abilities. Explicit structure is inherent in hierarchical compositional models, however, these lack the ability to optimize a well-defined cost function. We propose a novel analytic model of a basic unit in a layered hierarchical model with both explicit compositional structure and a well-defined discriminative cost function. Our experiments on two datasets show that the proposed compositional model performs on a par with standard CNNs on discriminative tasks, while, due to explicit modeling of the structure in the feature units, affording a straight-forward visualization of parts and faster inference due to separability of the units.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Adding discriminative power to a generative hierarchical compositional model using histograms of compositionsComputer Vision and Image Understanding, 2015
- Understanding deep image representations by inverting them2015
- Learning AND-OR Templates for Object Recognition and DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Adding Discriminative Power to Hierarchical Compositional Models for Object Class DetectionLecture Notes in Computer Science, 2013
- Transforming Auto-Encoders2011
- Learning Hierarchical Representations of Object Categories for Robot Vision2010
- Learning a Hierarchical Deformable Template for Rapid Deformable Object ParsingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Towards Scalable Representations of Object Categories: Learning a Hierarchy of Parts2007
- Histograms of Oriented Gradients for Human Detection2005
- Object recognition from local scale-invariant features1999