Adversarial Virtual Exemplar Learning for Label-Frugal Satellite Image Change Detection

TL;DR

This paper introduces an adversarial active learning approach for satellite image change detection that efficiently selects the most informative virtual exemplars to improve detection accuracy with minimal oracle queries.

Contribution

It proposes a novel adversarial model for active learning that selects diverse and uncertain virtual exemplars to enhance change detection in satellite images.

Findings

Outperforms existing display strategies in experiments

Reduces the number of oracle queries needed for accurate detection

Improves change detection accuracy through adversarial virtual exemplars

Abstract

Satellite image change detection aims at finding occurrences of targeted changes in a given scene taken at different instants. This task is highly challenging due to the acquisition conditions and also to the subjectivity of changes. In this paper, we investigate satellite image change detection using active learning. Our method is interactive and relies on a question and answer model which asks the oracle (user) questions about the most informative display (dubbed as virtual exemplars), and according to the user's responses, updates change detections. The main contribution of our method consists in a novel adversarial model that allows frugally probing the oracle with only the most representative, diverse and uncertain virtual exemplars. The latter are learned to challenge the most the trained change decision criteria which ultimately leads to a better re-estimate of these criteria in the following iterations of active learning. Conducted experiments show the out-performance of our proposed adversarial display model against other display strategies as well as the related work.