Compressed Domain Image Classification Using a Dynamic-Rate Neural Network

Abstract

Compressed domain image classification performs classification directly on compressive measurements acquired from the single-pixel camera, bypassing the image reconstruction step. It is of great importance for extending high-speed object detection and classification beyond the visible spectrum in a cost-effective manner especially for resource-limited platforms. Previous neural network methods require training a dedicated neural network for each different measurement rate (MR), which is costly in computation and storage. In this work, we develop an efficient training scheme that provides a neural network with dynamic-rate property, where a single neural network is capable of classifying over any MR within the range of interest with a given sensing matrix. This training scheme uses only a few selected MRs for training and the trained neural network is valid over the full range of MRs of interest. We demonstrate the performance of the dynamic-rate neural network on datasets of MNIST, CIFAR-10, Fashion-MNIST, COIL-100, and show that it generates approximately equal performance at each MR as that of a single-rate neural network valid only for one MR. Robustness to noise of the dynamic-rate model is also demonstrated. The dynamic-rate training scheme can be regarded as a general approach compatible with different types of sensing matrices, various neural network architectures, and is a valuable step towards wider adoption of compressive inference techniques and other compressive sensing related tasks via neural networks.

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Learned D-AMP: Principled Neural Network based Compressive Image Recovery
• Compressed sensing performance bounds under Poisson noise
• Compressed Learning: A Deep Neural Network Approach
• Rate-Adaptive Neural Networks for Spatial Multiplexers

Cited by in corpus (6)

• COAST: COntrollable Arbitrary-Sampling NeTwork for Compressive Sensing
• Non-imaging single-pixel sensing with optimized binary modulation
• Multilinear Compressive Learning
• A high performance approach to detecting small targets in long range low quality infrared videos
• Deep Learning Techniques for Compressive Sensing-Based Reconstruction and Inference -- A Ubiquitous Systems Perspective
• Scalable Deep Compressive Sensing