JL1-CD：遙感變化檢測的新基準與穩健的多教師知識蒸餾框架

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

深度學習在遙感影像變化檢測（CD）領域已取得顯著成功，但仍面臨兩大挑戰：一是缺乏亞米級、全面性的開源CD數據集，二是在變化區域多樣的影像中難以實現一致且令人滿意的檢測結果。為解決這些問題，我們引入了JL1-CD數據集，該數據集包含5000對512×512像素的影像，分辨率為0.5至0.75米。此外，我們提出了一種用於CD的多教師知識蒸餾（MTKD）框架。在JL1-CD和SYSU-CD數據集上的實驗結果表明，MTKD框架顯著提升了不同網絡架構和參數規模的CD模型性能，達到了新的最佳水平。代碼已公開於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.