Аннотация:
Metric-based representation learning showed good accuracy in identifying objects from one-dimensional spectroscopy data, robustness to small dataset size and the ability to change the data domain without fine-tuning.
Образец цитирования:
A. P. Vorozhtsov, P. V. Kitina, “Contrastive representation learning for spectroscopy data analysis”, Mendeleev Commun., 34:6 (2024), 786–787