CondenseNeXt: An Ultra-Efficient Deep Neural Network for Embedded Systems
- 27 January 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 0524-0528
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.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- CondenseNet: An Efficient DenseNet Using Learned Group Convolutions2018
- ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression2017
- Densely Connected Convolutional Networks2017
- Xception: Deep Learning with Depthwise Separable Convolutions2017
- Aggregated Residual Transformations for Deep Neural Networks2017
- Accelerating convolutional neural networks by group-wise 2D-filter pruning2017
- Deep Residual Learning for Image Recognition2016
- Fast ConvNets Using Group-Wise Brain Damage2016
- Simplifying ConvNets for Fast Learning2012
- Polynomial Theory of Complex SystemsIEEE Transactions on Systems, Man, and Cybernetics, 1971