Augmenting Deep Classifiers with Polynomial Neural Networks

TL;DR

This paper introduces a unifying polynomial framework for deep classifiers, enhancing understanding, performance, and adaptability of neural networks across image and audio tasks.

Contribution

It presents a novel polynomial-based taxonomy that unifies various deep architectures and enables extensions for improved performance and data efficiency.

Findings

Enhanced model performance on standard benchmarks

Improved model compression capabilities

Benefits in limited and long-tailed data scenarios

Abstract

Deep neural networks have been the driving force behind the success in classification tasks, e.g., object and audio recognition. Impressive results and generalization have been achieved by a variety of recently proposed architectures, the majority of which are seemingly disconnected. In this work, we cast the study of deep classifiers under a unifying framework. In particular, we express state-of-the-art architectures (e.g., residual and non-local networks) in the form of different degree polynomials of the input. Our framework provides insights on the inductive biases of each model and enables natural extensions building upon their polynomial nature. The efficacy of the proposed models is evaluated on standard image and audio classification benchmarks. The expressivity of the proposed models is highlighted both in terms of increased model performance as well as model compression. Lastly, the extensions allowed by this taxonomy showcase benefits in the presence of limited data and long-tailed data distributions. We expect this taxonomy to provide links between existing domain-specific architectures. The source code is available at \url{https://github.com/grigorisg9gr/polynomials-for-augmenting-NNs}.