arXiv cs.AI· Xavier Bou, Elliot Vincent, Gabriele Facciolo, Rafael Grompone von Gioi, Jean-Michel Morel, Thibaud Ehret·· 3 小时前AI 评分37
基于弱时间监督的遥感变化检测方法研究
Remote Sensing Change Detection via Weak Temporal Supervision
AI 导读
研究者提出一种弱时间监督策略，利用现有单时相遥感数据集的额外时相观测来训练变化检测模型，无需新的像素级标注。该方法假设真实双时相图像对大多无变化，并用不同位置的图像配对生成变化样本，通过物体感知的变化图生成与迭代精化处理弱标签噪声。在 FLAIR 和 IAILD 航拍数据集扩展版本上验证，取得有竞争力的 zero-shot 与低数据表现，并在法国大范围区域展示了可扩展性。
正文 · 原文
Abstract:Semantic change detection in remote sensing aims to identify land cover changes between bi-temporal image pairs. Progress in this area has been limited by the scarcity of annotated datasets, as pixel-level annotation is costly and time-consuming. To address this, recent methods leverage synthetic data or generate artificial change pairs, but transferring change detection models across datasets and acquisition conditions remains challenging. In this work, we introduce a weak temporal supervision strategy that leverages additional temporal observations of existing single-temporal datasets, without requiring any new annotations. Specifically, we extend single-date remote sensing datasets with new observations acquired at different times and train a change detection model by assuming that real bi-temporal pairs mostly contain no change, while pairing images from different locations to generate change examples. To handle the inherent noise in these weak labels, we employ an object-aware change map generation and an iterative refinement process. We validate our approach on extended versions of the FLAIR and IAILD aerial datasets, showing competitive zero-shot and low-data regime performance. Lastly, we showcase results over large areas in France, highlighting the scalability potential of our method.
| Comments: | Accepted at WACV2027 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2601.02126 [cs.CV] |
| (or arXiv:2601.02126v3 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2601.02126 arXiv-issued DOI via DataCite |
Submission history
From: Elliot Vincent [view email]
[v1]
Mon, 5 Jan 2026 13:57:02 UTC (37,261 KB)
[v2]
Fri, 6 Nov 2026 11:43:28 UTC (36,812 KB)
[v3]
Tue, 10 Nov 2026 12:53:44 UTC (36,802 KB)
来源：arXiv cs.AI · arxiv.org