Related papers: Adaptive Hierarchical Decomposition of Large Deep Networks

Adaptive Hierarchical Decomposition of Large Deep Networks

URL: http://arxiv.org/abs/2008.00809v1
Date: Fri, 17 Jul 2020 21:04:50 GMT
Title: Adaptive Hierarchical Decomposition of Large Deep Networks
Authors: Sumanth Chennupati, Sai Nooka, Shagan Sah, Raymond W Ptucha
Abstract summary: As datasets get larger, a natural question is if existing deep learning architectures can be extended to handle the 50+K classes thought to be perceptible by a typical human. This paper introduces a framework that automatically analyzes and configures a family of smaller deep networks as a replacement to a singular, larger network. The resulting smaller networks are highly scalable, parallel and more practical to train, and achieve higher classification accuracy.
Score: 4.272649614101117
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Deep learning has recently demonstrated its ability to rival the human brain for visual object recognition. As datasets get larger, a natural question to ask is if existing deep learning architectures can be extended to handle the 50+K classes thought to be perceptible by a typical human. Most deep learning architectures concentrate on splitting diverse categories, while ignoring the similarities amongst them. This paper introduces a framework that automatically analyzes and configures a family of smaller deep networks as a replacement to a singular, larger network. Class similarities guide the creation of a family from course to fine classifiers which solve categorical problems more effectively than a single large classifier. The resulting smaller networks are highly scalable, parallel and more practical to train, and achieve higher classification accuracy. This paper also proposes a method to adaptively select the configuration of the hierarchical family of classifiers using linkage statistics from overall and sub-classification confusion matrices. Depending on the number of classes and the complexity of the problem, a deep learning model is selected and the complexity is determined. Numerous experiments on network classes, layers, and architecture configurations validate our results.