Adaptive Hierarchical Decomposition of Large Deep Networks
This addresses the challenge of scaling deep learning to large-scale classification tasks, such as visual object recognition with 50K+ classes, by improving efficiency and accuracy.
The paper tackles the problem of scaling deep networks to handle tens of thousands of classes by introducing a framework that replaces a single large network with a hierarchical family of smaller networks guided by class similarities, resulting in higher classification accuracy and more practical training.
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.