Active Deep Probabilistic Subsampling
Hans Van Gorp, Iris Huijben, Bastiaan S Veeling, Nicola Pezzotti, Ruud J. G. Van Sloun
Abstract
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.
BibTeX
@InProceedings{pmlr-v139-van-gorp21a,
title = {Active Deep Probabilistic Subsampling},
author = {Van Gorp, Hans and Huijben, Iris and Veeling, Bastiaan S and Pezzotti, Nicola and Van Sloun, Ruud J. G.},
booktitle = {Proceedings of the 38th International Conference on Machine Learning},
pages = {10509--10518},
year = {2021},
editor = {Meila, Marina and Zhang, Tong},
volume = {139},
series = {Proceedings of Machine Learning Research},
month = {18--24 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v139/van-gorp21a/van-gorp21a.pdf},
url = {https://proceedings.mlr.press/v139/van-gorp21a.html},
abstract = {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.}
}