Compressed Domain Image Classification Using a Dynamic-Rate Neural Network
Authors:
Open Access
- 1 December 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 217711-217722
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.Keywords
All Related Versions
Funding Information
- National Science Foundation (CHE1610453)
- Air Force Office of Scientific Research (FA8651-16-C-0185)
This publication has 25 references indexed in Scilit:
- Reconstruction-Free Action Inference from Compressive ImagersIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Reconstruction-free inference on compressive measurements2015
- Compressive image acquisition and classification via secant projectionsJournal of Optics, 2015
- Compressive Sensing with Partial-Complete, Multiscale Hadamard Waveforms2013
- Stable Image Reconstruction Using Total Variation MinimizationSIAM Journal on Imaging Sciences, 2013
- A single-pixel terahertz imaging system based on compressed sensingApplied Physics Letters, 2008
- The smashed filter for compressive classification and target recognition2007
- Decoding by Linear ProgrammingIEEE Transactions on Information Theory, 2005
- Object recognition from local scale-invariant features1999
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998