JL1-CD：遥感变化检测新基准与鲁棒多教师知识蒸馏框架

JL1-CD: A New Benchmark for Remote Sensing Change Detection and a Robust Multi-Teacher Knowledge Distillation Framework

February 19, 2025

作者: Ziyuan Liu, Ruifei Zhu, Long Gao, Yuanxiu Zhou, Jingyu Ma, Yuantao Gu

cs.AI

摘要

深度学习在遥感图像变化检测（CD）领域已取得显著成就，但仍面临两大挑战：一是亚米级、全面覆盖的开源CD数据集稀缺，二是在变化区域差异显著的图像间实现一致且令人满意的检测结果存在困难。针对这些问题，我们推出了JL1-CD数据集，该数据集包含5000对512×512像素的图像，分辨率为0.5至0.75米。此外，我们提出了一种多教师知识蒸馏（MTKD）框架用于变化检测。在JL1-CD和SYSU-CD数据集上的实验结果表明，MTKD框架显著提升了不同网络架构与参数规模下CD模型的性能，达到了新的技术前沿水平。相关代码已公开于https://github.com/circleLZY/MTKD-CD。

English

Deep learning has achieved significant success in the field of remote sensing image change detection (CD), yet two major challenges remain: the scarcity of sub-meter, all-inclusive open-source CD datasets, and the difficulty of achieving consistent and satisfactory detection results across images with varying change areas. To address these issues, we introduce the JL1-CD dataset, which contains 5,000 pairs of 512 x 512 pixel images with a resolution of 0.5 to 0.75 meters. Additionally, we propose a multi-teacher knowledge distillation (MTKD) framework for CD. Experimental results on the JL1-CD and SYSU-CD datasets demonstrate that the MTKD framework significantly improves the performance of CD models with various network architectures and parameter sizes, achieving new state-of-the-art results. The code is available at https://github.com/circleLZY/MTKD-CD.