Novel Batch Active Learning Approach and Its Application to Synthetic Aperture Radar Datasets

TL;DR

This paper introduces a novel batch active learning method combining DAC and LocalMax, achieving comparable accuracy to sequential methods but with greater efficiency, demonstrated on SAR datasets with a transfer learning pipeline.

Contribution

A new two-part batch active learning approach that maintains accuracy while improving efficiency for SAR data classification.

Findings

DAC and LocalMax achieve near-sequential accuracy

The method is more efficient proportional to batch size

Outperforms state-of-the-art CNN methods on SAR datasets

Abstract

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.