Frugal Satellite Image Change Detection with Deep-Net Inversion

TL;DR

This paper introduces a novel active learning algorithm for satellite image change detection that uses deep-net inversion to efficiently identify critical change instances with minimal user input.

Contribution

It proposes a new adversarial model leveraging deep-net inversion to select diverse and uncertain virtual exemplars, improving change detection accuracy with limited labeled data.

Findings

Outperforms existing change detection methods

Efficiently identifies critical change instances with minimal user queries

Enhances neural network training through adversarial virtual exemplars

Abstract

Change detection in satellite imagery seeks to find occurrences of targeted changes in a given scene taken at different instants. This task has several applications ranging from land-cover mapping, to anthropogenic activity monitory as well as climate change and natural hazard damage assessment. However, change detection is highly challenging due to the acquisition conditions and also to the subjectivity of changes. In this paper, we devise a novel algorithm for change detection based on active learning. The proposed method is based on a question and answer model that probes an oracle (user) about the relevance of changes only on a small set of critical images (referred to as virtual exemplars), and according to oracle's responses updates deep neural network (DNN) classifiers. The main contribution resides in a novel adversarial model that allows learning the most representative, diverse and uncertain virtual exemplars (as inverted preimages of the trained DNNs) that challenge (the most) the trained DNNs, and this leads to a better re-estimate of these networks in the subsequent iterations of active learning. Experiments show the out-performance of our proposed deep-net inversion against the related work.