Saved in:
Bibliographic Details
Main Authors: Chen, Jiyi, Li, Pengyu, Wang, Yutong, Ku, Pei-Cheng, Qu, Qing
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.12354
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929462375874560
author Chen, Jiyi
Li, Pengyu
Wang, Yutong
Ku, Pei-Cheng
Qu, Qing
author_facet Chen, Jiyi
Li, Pengyu
Wang, Yutong
Ku, Pei-Cheng
Qu, Qing
contents This work proposes a deep learning (DL)-based framework, namely Sim2Real, for spectral signal reconstruction in reconstructive spectroscopy, focusing on efficient data sampling and fast inference time. The work focuses on the challenge of reconstructing real-world spectral signals under the extreme setting where only device-informed simulated data are available for training. Such device-informed simulated data are much easier to collect than real-world data but exhibit large distribution shifts from their real-world counterparts. To leverage such simulated data effectively, a hierarchical data augmentation strategy is introduced to mitigate the adverse effects of this domain shift, and a corresponding neural network for the spectral signal reconstruction with our augmented data is designed. Experiments using a real dataset measured from our spectrometer device demonstrate that Sim2Real achieves significant speed-up during the inference while attaining on-par performance with the state-of-the-art optimization-based methods.
format Preprint
id arxiv_https___arxiv_org_abs_2403_12354
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sim2Real in Reconstructive Spectroscopy: Deep Learning with Augmented Device-Informed Data Simulation
Chen, Jiyi
Li, Pengyu
Wang, Yutong
Ku, Pei-Cheng
Qu, Qing
Machine Learning
Signal Processing
This work proposes a deep learning (DL)-based framework, namely Sim2Real, for spectral signal reconstruction in reconstructive spectroscopy, focusing on efficient data sampling and fast inference time. The work focuses on the challenge of reconstructing real-world spectral signals under the extreme setting where only device-informed simulated data are available for training. Such device-informed simulated data are much easier to collect than real-world data but exhibit large distribution shifts from their real-world counterparts. To leverage such simulated data effectively, a hierarchical data augmentation strategy is introduced to mitigate the adverse effects of this domain shift, and a corresponding neural network for the spectral signal reconstruction with our augmented data is designed. Experiments using a real dataset measured from our spectrometer device demonstrate that Sim2Real achieves significant speed-up during the inference while attaining on-par performance with the state-of-the-art optimization-based methods.
title Sim2Real in Reconstructive Spectroscopy: Deep Learning with Augmented Device-Informed Data Simulation
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2403.12354