Image augmentation with invertible networks in interactive satellite image change detection

TL;DR

This paper introduces an interactive satellite image change detection method that uses invertible networks for data augmentation within an active learning framework, improving detection accuracy.

Contribution

The novel invertible network enables effective data augmentation in change detection, enhancing active learning with dynamic model updates.

Findings

Superior performance over existing methods

Effective data augmentation with invertible networks

Improved change detection accuracy

Abstract

This paper devises a novel interactive satellite image change detection algorithm based on active learning. Our framework employs an iterative process that leverages a question-and-answer model. This model queries the oracle (user) about the labels of a small subset of images (dubbed as display), and based on the oracle's responses, change detection model is dynamically updated. The main contribution of our framework resides in a novel invertible network that allows augmenting displays, by mapping them from highly nonlinear input spaces to latent ones, where augmentation transformations become linear and more tractable. The resulting augmented data are afterwards mapped back to the input space, and used to retrain more effective change detection criteria in the subsequent iterations of active learning. Experimental results demonstrate superior performance of our proposed method compared to the related work.