Reinforcement-based Display-size Selection for Frugal Satellite Image Change Detection
This work addresses the challenge of efficient change detection in satellite imagery for remote sensing applications, but it appears incremental as it builds on existing active learning methods.
The paper tackles the problem of interactive satellite image change detection by introducing a reinforcement learning approach that frugally selects critical images for user annotation, achieving better generalization in experiments.
We introduce a novel interactive satellite image change detection algorithm based on active learning. The proposed method is iterative and consists in frugally probing the user (oracle) about the labels of the most critical images, and according to the oracle's annotations, it updates change detection results. First, we consider a probabilistic framework which assigns to each unlabeled sample a relevance measure modeling how critical is that sample when training change detection functions. We obtain these relevance measures by minimizing an objective function mixing diversity, representativity and uncertainty. These criteria when combined allow exploring different data modes and also refining change detections. Then, we further explore the potential of this objective function, by considering a reinforcement learning approach that finds the best combination of diversity, representativity and uncertainty as well as display-sizes through active learning iterations, leading to better generalization as shown through experiments in interactive satellite image change detection.