Quantitative Analysis of Image Classification Techniques for Memory-Constrained Devices
This work addresses the challenge of deploying image classification models on embedded devices with limited memory, but it is incremental as it extends existing methods to multi-channel images and benchmarks them.
The paper tackled the problem of image classification on memory-constrained devices by comparing CNNs with memory-efficient algorithms like ProtoNN, Bonsai, and FastGRNN on CIFAR-10, finding that Direct Convolution CNNs achieved the best performance with 65.7% accuracy at 58.23KB memory footprint.
Convolutional Neural Networks, or CNNs, are the state of the art for image classification, but typically come at the cost of a large memory footprint. This limits their usefulness in applications relying on embedded devices, where memory is often a scarce resource. Recently, there has been significant progress in the field of image classification on such memory-constrained devices, with novel contributions like the ProtoNN, Bonsai and FastGRNN algorithms. These have been shown to reach up to 98.2% accuracy on optical character recognition using MNIST-10, with a memory footprint as little as 6KB. However, their potential on more complex multi-class and multi-channel image classification has yet to be determined. In this paper, we compare CNNs with ProtoNN, Bonsai and FastGRNN when applied to 3-channel image classification using CIFAR-10. For our analysis, we use the existing Direct Convolution algorithm to implement the CNNs memory-optimally and propose new methods of adjusting the FastGRNN model to work with multi-channel images. We extend the evaluation of each algorithm to a memory size budget of 8KB, 16KB, 32KB, 64KB and 128KB to show quantitatively that Direct Convolution CNNs perform best for all chosen budgets, with a top performance of 65.7% accuracy at a memory footprint of 58.23KB.