DeepAI AI Chat
Log In Sign Up

Compressed domain image classification using a multi-rate neural network

by   Yibo Xu, et al.

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.


Compressed Learning: A Deep Neural Network Approach

Compressed Learning (CL) is a joint signal processing and machine learni...

Transform and Bitstream Domain Image Classification

Classification of images within the compressed domain offers significant...

Compressively Sensed Image Recognition

Compressive Sensing (CS) theory asserts that sparse signal reconstructio...

Rate-Adaptive Neural Networks for Spatial Multiplexers

In resource-constrained environments, one can employ spatial multiplexin...

Use of First and Third Person Views for Deep Intersection Classification

We explore the problem of intersection classification using monocular on...

Non-imaging single-pixel sensing with optimized binary modulation

The conventional high-level sensing tasks such as image classification r...

On Hyperspectral Classification in the Compressed Domain

In this paper, we study the problem of hyperspectral pixel classificatio...