Change Detection Meets Visual Question Answering

TL;DR

This paper introduces a new task called change detection-based visual question answering (CDVQA) that enables users to query high-level change information from multi-temporal aerial images, supported by a new dataset and baseline framework.

Contribution

The paper presents the first CDVQA dataset, a baseline model with a change enhancing module, and analyzes different fusion strategies for the task.

Findings

The change enhancing module improves change-related information capture.

Different fusion strategies significantly affect CDVQA performance.

The dataset and baseline provide a foundation for future research in CDVQA.

Abstract

The Earth's surface is continually changing, and identifying changes plays an important role in urban planning and sustainability. Although change detection techniques have been successfully developed for many years, these techniques are still limited to experts and facilitators in related fields. In order to provide every user with flexible access to change information and help them better understand land-cover changes, we introduce a novel task: change detection-based visual question answering (CDVQA) on multi-temporal aerial images. In particular, multi-temporal images can be queried to obtain high level change-based information according to content changes between two input images. We first build a CDVQA dataset including multi-temporal image-question-answer triplets using an automatic question-answer generation method. Then, a baseline CDVQA framework is devised in this work, and it contains four parts: multi-temporal feature encoding, multi-temporal fusion, multi-modal fusion, and answer prediction. In addition, we also introduce a change enhancing module to multi-temporal feature encoding, aiming at incorporating more change-related information. Finally, effects of different backbones and multi-temporal fusion strategies are studied on the performance of CDVQA task. The experimental results provide useful insights for developing better CDVQA models, which are important for future research on this task.