A Comprehensive Study of MCS-TCL: Multi-Functional Sampling for Trustworthy Compressive Learning
Open Access
- 7 September 2025
- journal article
- research article
- Published by MDPI AG in Information
- Vol. 16 (9) , 777
Abstract
Compressive Learning (CL) is an emerging paradigm that allows machine learning models to perform inference directly from compressed measurements, significantly reducing sensing and computational costs. While existing CL approaches have achieved competitive accuracy compared to traditional image-domain methods, they typically rely on reconstruction to address information loss and often neglect uncertainty arising from ambiguous or insufficient data. In this work, we propose MCS-TCL, a novel and trustworthy CL framework based on Multi-functional Compressive Sensing Sampling. Our approach unifies sampling, compression, and feature extraction into a single operation by leveraging the compatibility between compressive sensing and convolutional feature learning. This joint design enables efficient signal acquisition while preserving discriminative information, leading to feature representations that remain robust across varying sampling ratios. To enhance the model’s reliability, we incorporate evidential deep learning (EDL) during training. EDL estimates the distribution of evidence over output classes, enabling the model to quantify predictive uncertainty and assign higher confidence to well-supported predictions. Extensive experiments on image classification tasks show that MCS-TCL outperforms existing CL methods, achieving state-of-the-art accuracy at a low sampling rate of 6%. Additionally, our framework reduces model size by 85.76% while providing meaningful uncertainty estimates, demonstrating its effectiveness in resource-constrained learning scenarios.Keywords
Funding Information
- JSPS KAKENHI (JP22K12101)
This publication has 54 references indexed in Scilit:
- Optimization-Inspired Compact Deep Compressive SensingIEEE Journal of Selected Topics in Signal Processing, 2020
- Compressed Learning for Tactile Object RecognitionIEEE Robotics and Automation Letters, 2018
- Remote Sensing Image Scene Classification: Benchmark and State of the ArtProceedings of the IEEE, 2017
- Direct inference on compressive measurements using convolutional neural networks2016
- Image compressive sensing recovery using adaptively learned sparsifying basis via L0 minimizationSignal Processing, 2014
- Imaging With Nature: Compressive Imaging Using a Multiply Scattering MediumScientific Reports, 2014
- Projections designs for compressive classification2013
- Random Projections of Smooth ManifoldsFoundations of Computational Mathematics, 2007
- Compressive Sampling for Signal Classification2006
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998