Generative Sensing: Transforming Unreliable Sensor Data for Reliable Recognition

TL;DR

This paper presents a deep learning framework that enhances low-quality sensor data to achieve recognition accuracy comparable to high-end sensors, by transforming data into higher quality or different modalities.

Contribution

It introduces a discriminative, recognition-focused generative sensing framework with selective feature regeneration, differing from traditional image generation methods.

Findings

Achieves high recognition accuracy with low-end sensors

Transforms low-quality data into high-quality or different modality data

Demonstrates improved robustness in perception tasks

Abstract

This paper introduces a deep learning enabled generative sensing framework which integrates low-end sensors with computational intelligence to attain a high recognition accuracy on par with that attained with high-end sensors. The proposed generative sensing framework aims at transforming low-end, low-quality sensor data into higher quality sensor data in terms of achieved classification accuracy. The low-end data can be transformed into higher quality data of the same modality or into data of another modality. Different from existing methods for image generation, the proposed framework is based on discriminative models and targets to maximize the recognition accuracy rather than a similarity measure. This is achieved through the introduction of selective feature regeneration in a deep neural network (DNN). The proposed generative sensing will essentially transform low-quality sensor data into high-quality information for robust perception. Results are presented to illustrate the performance of the proposed framework.