Active Deep Probabilistic Subsampling
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 learns an optimal sampling pattern in a challenging toy problem and improves over DPS for MNIST classification at high subsampling rates. We observe that ADPS learns to actively adapt based on the previously sampled elements, yielding different sampling sequences across the dataset. Finally, we demonstrate strong performance in active acquisition Magnetic Resonance Image (MRI) reconstruction, outperforming DPS and other deep learning methods.
PDF Abstract