Search papers, labs, and topics across Lattice.
This paper enhances the Active Deep Probabilistic Subsampling (A-DPS) method by introducing Prior-aware and Context-guided Group-based Active DPS (PGA-DPS), which incorporates a deterministic prior-informed sampling pattern and employs group-based top-k sampling. By leveraging dataset priors and optimizing sampling trajectories, PGA-DPS achieves more robust performance across various tasks, including classification and image reconstruction. Empirical evaluations demonstrate that PGA-DPS consistently outperforms A-DPS and other existing sampling methods across multiple datasets, indicating significant improvements in optimization efficacy.
PGA-DPS outperforms traditional sampling methods by integrating dataset priors and group sampling, leading to superior optimization in real-world applications.
Subsampling significantly reduces the number of measurements, thereby streamlining data processing and transfer overhead, and shortening acquisition time across diverse real-world applications. The recently introduced Active Deep Probabilistic Subsampling (A-DPS) approach jointly optimizes both the subsampling pattern and the downstream task model, enabling instance- and subject-specific sampling trajectories and effective adaptation to new data at inference time. However, this approach does not fully leverage valuable dataset priors and relies on top-1 sampling, which can impede the optimization process. Herein, we enhance A-DPS by integrating a deterministic (fixed) prior-informed sampling pattern derived from the training dataset, along with group-based sampling via top-k sampling, to achieve more robust optimization, method we call Prior-aware and context-guided Group-based Active DPS (PGA-DPS). We also provide a theoretical analysis supporting improved optimization via group sampling, and validate this with empirical results. We evaluated PGA-DPS on three tasks: classification, image reconstruction, and segmentation, using the MNIST, CIFAR-10, fastMRI knee, and hyperspectral AeroRIT datasets, respectively. In every case, PGA-DPS outperformed A-DPS, DPS, and all other sampling methods.
