Architectural Innovations for Efficient Denoising and Classification
A Manual vs. Neural Architecture Search Comparison
T.C. Markhorst (TU Delft - Electrical Engineering, Mathematics and Computer Science)
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)
More Info
expand_more
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.