CondenseNeXt: An Ultra-Efficient Deep Neural Network for Embedded Systems

TL;DR

CondenseNeXt is a novel, highly efficient deep neural network architecture designed for real-time image classification on resource-constrained embedded systems, reducing computational costs while maintaining accuracy.

Contribution

This paper introduces CondenseNeXt, a new CNN variant that significantly reduces parameters and FLOPs compared to CondenseNet, enabling efficient on-device inference.

Findings

Reduces trainable parameters and FLOPs significantly.

Maintains high accuracy with a model size under 3 MB.

Achieves superior efficiency for embedded system deployment.

Abstract

Due to the advent of modern embedded systems and mobile devices with constrained resources, there is a great demand for incredibly efficient deep neural networks for machine learning purposes. There is also a growing concern of privacy and confidentiality of user data within the general public when their data is processed and stored in an external server which has further fueled the need for developing such efficient neural networks for real-time inference on local embedded systems. The scope of our work presented in this paper is limited to image classification using a convolutional neural network. A Convolutional Neural Network (CNN) is a class of Deep Neural Network (DNN) widely used in the analysis of visual images captured by an image sensor, designed to extract information and convert it into meaningful representations for real-time inference of the input data. In this paper, we propose a neoteric variant of deep convolutional neural network architecture to ameliorate the performance of existing CNN architectures for real-time inference on embedded systems. We show that this architecture, dubbed CondenseNeXt, is remarkably efficient in comparison to the baseline neural network architecture, CondenseNet, by reducing trainable parameters and FLOPs required to train the network whilst maintaining a balance between the trained model size of less than 3.0 MB and accuracy trade-off resulting in an unprecedented computational efficiency.