Image Classification with CondenseNeXt for ARM-Based Computing Platforms
This addresses the problem of efficient image classification for self-driving vehicles and other ARM-based embedded systems with limited computational resources, representing an incremental improvement over existing methods.
The paper tackles image classification for ARM-based embedded platforms by proposing CondenseNeXt, an ultra-efficient CNN architecture that achieves state-of-the-art performance on CIFAR-10 (4.79% top-1 error), CIFAR-100 (21.98% top-1 error), and ImageNet (7.91% top-5 error), with up to 59.98% reduction in FLOPs and 2.9+ MB model size improvement compared to CondenseNet.
In this paper, we demonstrate the implementation of our ultra-efficient deep convolutional neural network architecture: CondenseNeXt on NXP BlueBox, an autonomous driving development platform developed for self-driving vehicles. We show that CondenseNeXt is remarkably efficient in terms of FLOPs, designed for ARM-based embedded computing platforms with limited computational resources and can perform image classification without the need of a CUDA enabled GPU. CondenseNeXt utilizes the state-of-the-art depthwise separable convolution and model compression techniques to achieve a remarkable computational efficiency. Extensive analyses are conducted on CIFAR-10, CIFAR-100 and ImageNet datasets to verify the performance of CondenseNeXt Convolutional Neural Network (CNN) architecture. It achieves state-of-the-art image classification performance on three benchmark datasets including CIFAR-10 (4.79% top-1 error), CIFAR-100 (21.98% top-1 error) and ImageNet (7.91% single model, single crop top-5 error). CondenseNeXt achieves final trained model size improvement of 2.9+ MB and up to 59.98% reduction in forward FLOPs compared to CondenseNet and can perform image classification on ARM-Based computing platforms without needing a CUDA enabled GPU support, with outstanding efficiency.