Change is Everywhere: Single-Temporal Supervised Object Change Detection in Remote Sensing Imagery

TL;DR

This paper introduces STAR, a novel single-temporal supervised learning approach for remote sensing change detection that uses unpaired images for training, reducing the need for costly pairwise labeling.

Contribution

The paper proposes STAR, enabling high-accuracy change detection with only unpaired labeled images and introduces ChangeStar, a flexible change detector architecture.

Findings

ChangeStar outperforms baseline methods under single-temporal supervision.

ChangeStar achieves superior performance compared to traditional bitemporal supervised methods.

The approach reduces the need for expensive pairwise labeled data.

Abstract

For high spatial resolution (HSR) remote sensing images, bitemporal supervised learning always dominates change detection using many pairwise labeled bitemporal images. However, it is very expensive and time-consuming to pairwise label large-scale bitemporal HSR remote sensing images. In this paper, we propose single-temporal supervised learning (STAR) for change detection from a new perspective of exploiting object changes in unpaired images as supervisory signals. STAR enables us to train a high-accuracy change detector only using \textbf{unpaired} labeled images and generalize to real-world bitemporal images. To evaluate the effectiveness of STAR, we design a simple yet effective change detector called ChangeStar, which can reuse any deep semantic segmentation architecture by the ChangeMixin module. The comprehensive experimental results show that ChangeStar outperforms the baseline with a large margin under single-temporal supervision and achieves superior performance under bitemporal supervision. Code is available at https://github.com/Z-Zheng/ChangeStar