Sim2Real in reconstructive spectroscopy: Deep learning with augmented device-informed data simulation

Authors:
Open Access
Publisher website
Google Scholar
Abstract
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 in an 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.
Funding Information
  • Division of Computing and Communication Foundations (2143904, 2212066)
  • Michigan Institute for Data Science, University of Michigan (PODS)
  • Division of Electrical, Communications and Cyber Systems (2317047)
  • KLA

This publication has 22 references indexed in Scilit: