DynamicEarth: How Far are We from Open-Vocabulary Change Detection?
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916577664827392 |
|---|---|
| author | Li, Kaiyu Cao, Xiangyong Deng, Yupeng Pang, Chao Xin, Zepeng Meng, Deyu Wang, Zhi |
| author_facet | Li, Kaiyu Cao, Xiangyong Deng, Yupeng Pang, Chao Xin, Zepeng Meng, Deyu Wang, Zhi |
| contents | Monitoring Earth's evolving land covers requires methods capable of detecting changes across a wide range of categories and contexts. Existing change detection methods are hindered by their dependency on predefined classes, reducing their effectiveness in open-world applications. To address this issue, we introduce open-vocabulary change detection (OVCD), a novel task that bridges vision and language to detect changes across any category. Considering the lack of high-quality data and annotation, we propose two training-free frameworks, M-C-I and I-M-C, which leverage and integrate off-the-shelf foundation models for the OVCD task. The insight behind the M-C-I framework is to discover all potential changes and then classify these changes, while the insight of I-M-C framework is to identify all targets of interest and then determine whether their states have changed. Based on these two frameworks, we instantiate to obtain several methods, e.g., SAM-DINOv2-SegEarth-OV, Grounding-DINO-SAM2-DINO, etc. Extensive evaluations on 5 benchmark datasets demonstrate the superior generalization and robustness of our OVCD methods over existing supervised and unsupervised methods. To support continued exploration, we release DynamicEarth, a dedicated codebase designed to advance research and application of OVCD. https://likyoo.github.io/DynamicEarth |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_12931 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DynamicEarth: How Far are We from Open-Vocabulary Change Detection? Li, Kaiyu Cao, Xiangyong Deng, Yupeng Pang, Chao Xin, Zepeng Meng, Deyu Wang, Zhi Computer Vision and Pattern Recognition Monitoring Earth's evolving land covers requires methods capable of detecting changes across a wide range of categories and contexts. Existing change detection methods are hindered by their dependency on predefined classes, reducing their effectiveness in open-world applications. To address this issue, we introduce open-vocabulary change detection (OVCD), a novel task that bridges vision and language to detect changes across any category. Considering the lack of high-quality data and annotation, we propose two training-free frameworks, M-C-I and I-M-C, which leverage and integrate off-the-shelf foundation models for the OVCD task. The insight behind the M-C-I framework is to discover all potential changes and then classify these changes, while the insight of I-M-C framework is to identify all targets of interest and then determine whether their states have changed. Based on these two frameworks, we instantiate to obtain several methods, e.g., SAM-DINOv2-SegEarth-OV, Grounding-DINO-SAM2-DINO, etc. Extensive evaluations on 5 benchmark datasets demonstrate the superior generalization and robustness of our OVCD methods over existing supervised and unsupervised methods. To support continued exploration, we release DynamicEarth, a dedicated codebase designed to advance research and application of OVCD. https://likyoo.github.io/DynamicEarth |
| title | DynamicEarth: How Far are We from Open-Vocabulary Change Detection? |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.12931 |