Compressed domain image classification using a multi-rate neural network

Compressed domain image classification aims to directly perform classification on compressive measurements generated from the single-pixel camera. While neural network approaches have achieved state-of-the-art performance, previous methods require training a dedicated network for each different measurement rate which is computationally costly. In this work, we present a general approach that endows a single neural network with multi-rate property for compressed domain classification where a single network is capable of classifying over an arbitrary number of measurements using dataset-independent fixed binary sensing patterns. We demonstrate the multi-rate neural network performance on MNIST and grayscale CIFAR-10 datasets. We also show that using the Partial Complete binary sensing matrix, the multi-rate network outperforms previous methods especially in the case of very few measurements.

The STONE Transform: Multi-Resolution Image Enhancement and Real-Time Compressive Video

Compressed sensing enables the reconstruction of high-resolution signals from under-sampled data. While compressive methods simplify data acquisition, they require the solution of difficult recovery problems to make use of the resulting measurements. This article presents a new sensing framework that combines the advantages of both conventional and compressive sensing. Using the proposed \stone transform, measurements can be reconstructed instantly at Nyquist rates at any power-of-two resolution. The same data can then be "enhanced" to higher resolutions using compressive methods that leverage sparsity to "beat" the Nyquist limit. The availability of a fast direct reconstruction enables compressive measurements to be processed on small embedded devices. We demonstrate this by constructing a real-time compressive video camera.