Abstract:
A large amount of labeled data is usually utilized to fully training forward prediction models, which results in a heavy labeling burden. Here, under constrained annotati...Show MoreMetadata
Abstract:
A large amount of labeled data is usually utilized to fully training forward prediction models, which results in a heavy labeling burden. Here, under constrained annotation resources, a scheme combining less selectively-labeled samples with cross-semi-supervised learning is proposed to accurately predict directional scattering from nanostructures. It is found that when only one-third dataset are labeled by numerical simulation, the prediction accuracy in this scheme is comparable to that of the conventional method based on fully-labeled data. Our findings greatly reduce the labeling cost for deep learning tasks in the field of nanophotonics and provide a new way to efficiently utilize limited data resources.
Published in: IEEE Photonics Technology Letters ( Volume: 37, Issue: 2, 15 January 2025)
Funding Agency:
No metrics found for this document.
No metrics found for this document.