Samenvatting
Subsampling a signal of interest can reduce costly data transfer, battery drain, radiation exposure and acquisition time in a wide range of problems. The recently proposed Deep Probabilistic Subsampling (DPS) method effectively integrates subsampling in an end-to-end deep learning model, but learns a static pattern for all datapoints. We generalize DPS to a sequential method that actively picks the next sample based on the information acquired so far; dubbed Active-DPS (A-DPS). We validate that A-DPS improves over DPS for MNIST classification at high subsampling rates. Moreover, we demonstrate strong performance in active acquisition Magnetic Resonance Image (MRI) reconstruction, outperforming DPS and other deep learning methods.
Originele taal-2 | Engels |
---|---|
Titel | 38th International Conference on Machine Learning |
Redacteuren | Marina Meila, Tong Zhang |
Uitgeverij | PMLR |
Pagina's | 10509-10518 |
Aantal pagina's | 10 |
ISBN van elektronische versie | 9781713845065 |
Status | Gepubliceerd - jul. 2021 |
Evenement | 38th International Conference on Machine Learning (ICML 2021) - Virtual Duur: 18 jul. 2021 → 24 jul. 2021 Congresnummer: 38 |
Publicatie series
Naam | Proceedings of Machine Learning Research |
---|---|
Volume | 139 |
ISSN van elektronische versie | 2640-3498 |
Congres
Congres | 38th International Conference on Machine Learning (ICML 2021) |
---|---|
Verkorte titel | ICML 2021 |
Periode | 18/07/21 → 24/07/21 |