Deep Active Learning in Remote Sensing for data efficient Change Detection

TL;DR

This paper explores active learning strategies for deep neural networks in remote sensing change detection, demonstrating significant reductions in annotation effort while maintaining high performance.

Contribution

It introduces and evaluates uncertainty estimation methods for active learning in deep models, achieving near-supervised performance with 99% fewer annotations.

Findings

Active learning effectively identifies informative samples.

The approach balances training data distribution automatically.

Achieves comparable performance to fully supervised models with minimal annotations.

Abstract

We investigate active learning in the context of deep neural network models for change detection and map updating. Active learning is a natural choice for a number of remote sensing tasks, including the detection of local surface changes: changes are on the one hand rare and on the other hand their appearance is varied and diffuse, making it hard to collect a representative training set in advance. In the active learning setting, one starts from a minimal set of training examples and progressively chooses informative samples that are annotated by a user and added to the training set. Hence, a core component of an active learning system is a mechanism to estimate model uncertainty, which is then used to pick uncertain, informative samples. We study different mechanisms to capture and quantify this uncertainty when working with deep networks, based on the variance or entropy across explicit or implicit model ensembles. We show that active learning successfully finds highly informative samples and automatically balances the training distribution, and reaches the same performance as a model supervised with a large, pre-annotated training set, with $\approx$99% fewer annotated samples.