JL1-CD: A New Benchmark for Remote Sensing Change Detection and a Robust Multi-Teacher Knowledge Distillation Framework
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914051651534848 |
|---|---|
| author | Liu, Ziyuan Zhu, Ruifei Gao, Long Zhou, Yuanxiu Ma, Jingyu Gu, Yuantao |
| author_facet | Liu, Ziyuan Zhu, Ruifei Gao, Long Zhou, Yuanxiu Ma, Jingyu Gu, Yuantao |
| contents | Change detection (CD) in remote sensing images plays a vital role in Earth observation. However, the scarcity of high-resolution, comprehensive open-source datasets and the difficulty in achieving robust performance across varying change types remain major challenges. To address these issues, we introduce JL1-CD, a large-scale, sub-meter CD dataset consisting of 5,000 image pairs. We further propose a novel Origin-Partition (O-P) strategy and integrate it into a Multi-Teacher Knowledge Distillation (MTKD) framework to enhance CD performance. The O-P strategy partitions the training set by Change Area Ratio (CAR) and trains specialized teacher models on each subset. The MTKD framework then distills complementary knowledge from these teachers into a single student model, enabling improved detection results across diverse CAR scenarios without additional inference cost. Our MTKD approach demonstrated strong performance in the 2024 ``Jilin-1'' Cup challenge, ranking first in the preliminary and second in the final rounds. Extensive experiments on the JL1-CD and SYSU-CD datasets show that the MTKD framework consistently improves the performance of CD models with various network architectures and parameter sizes, establishing new state-of-the-art results. Code and dataset are available at https://github.com/circleLZY/MTKD-CD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_13407 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | JL1-CD: A New Benchmark for Remote Sensing Change Detection and a Robust Multi-Teacher Knowledge Distillation Framework Liu, Ziyuan Zhu, Ruifei Gao, Long Zhou, Yuanxiu Ma, Jingyu Gu, Yuantao Computer Vision and Pattern Recognition Artificial Intelligence Change detection (CD) in remote sensing images plays a vital role in Earth observation. However, the scarcity of high-resolution, comprehensive open-source datasets and the difficulty in achieving robust performance across varying change types remain major challenges. To address these issues, we introduce JL1-CD, a large-scale, sub-meter CD dataset consisting of 5,000 image pairs. We further propose a novel Origin-Partition (O-P) strategy and integrate it into a Multi-Teacher Knowledge Distillation (MTKD) framework to enhance CD performance. The O-P strategy partitions the training set by Change Area Ratio (CAR) and trains specialized teacher models on each subset. The MTKD framework then distills complementary knowledge from these teachers into a single student model, enabling improved detection results across diverse CAR scenarios without additional inference cost. Our MTKD approach demonstrated strong performance in the 2024 ``Jilin-1'' Cup challenge, ranking first in the preliminary and second in the final rounds. Extensive experiments on the JL1-CD and SYSU-CD datasets show that the MTKD framework consistently improves the performance of CD models with various network architectures and parameter sizes, establishing new state-of-the-art results. Code and dataset are available at https://github.com/circleLZY/MTKD-CD. |
| title | JL1-CD: A New Benchmark for Remote Sensing Change Detection and a Robust Multi-Teacher Knowledge Distillation Framework |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2502.13407 |