Architectural Innovations for Efficient Denoising and Classification

A Manual vs. Neural Architecture Search Comparison

Master Thesis (2023)
Author(s)

T.C. Markhorst (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

Osman Semih Kayhan – Mentor (TU Delft - Pattern Recognition and Bioinformatics)

J.C. van Gemert – Mentor (TU Delft - Pattern Recognition and Bioinformatics)

Emir Demirovic – Graduation committee member (TU Delft - Algorithmics)

Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright
© 2023 Thomas Markhorst
More Info
expand_more
Publication Year
2023
Language
English
Copyright
© 2023 Thomas Markhorst
Graduation Date
22-08-2023
Awarding Institution
Delft University of Technology
Programme
['Computer Science | Artificial Intelligence']
Sponsors
Bosch Security Systems B.V.
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

In this paper, we combine image denoising and classification, aiming to enhance human perception of noisy images captured by edge devices, like security cameras. Since edge devices have little computational power, we also optimize for efficiency by proposing a novel architecture that integrates the two tasks. Additionally, we alter a Neural Architecture Search (NAS) method, which searches for classifiers, to search for the integrated model while optimizing for a target latency, classification accuracy, and denoising performance. Our NAS architectures outperform our manually designed alternatives in both denoising and classification, offering a significant improvement to human perception. Moreover, our approach empowers users to construct architectures tailored to domains like medical imaging, surveillance systems, and industrial inspections.

Files

License info not available