Novel Batch Active Learning Approach and Its Application to Synthetic Aperture Radar Datasets
This work addresses efficiency in active learning for synthetic aperture radar data classification, offering a domain-specific incremental improvement.
The authors tackled the challenge of maintaining model accuracy in batch active learning compared to sequential methods by developing a novel two-part approach (DAC and LocalMax), achieving nearly identical accuracy while improving efficiency proportional to batch size, and applied it to SAR datasets to outperform state-of-the-art CNN-based methods.
Active learning improves the performance of machine learning methods by judiciously selecting a limited number of unlabeled data points to query for labels, with the aim of maximally improving the underlying classifier's performance. Recent gains have been made using sequential active learning for synthetic aperture radar (SAR) data arXiv:2204.00005. In each iteration, sequential active learning selects a query set of size one while batch active learning selects a query set of multiple datapoints. While batch active learning methods exhibit greater efficiency, the challenge lies in maintaining model accuracy relative to sequential active learning methods. We developed a novel, two-part approach for batch active learning: Dijkstra's Annulus Core-Set (DAC) for core-set generation and LocalMax for batch sampling. The batch active learning process that combines DAC and LocalMax achieves nearly identical accuracy as sequential active learning but is more efficient, proportional to the batch size. As an application, a pipeline is built based on transfer learning feature embedding, graph learning, DAC, and LocalMax to classify the FUSAR-Ship and OpenSARShip datasets. Our pipeline outperforms the state-of-the-art CNN-based methods.