MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910463729598464 |
|---|---|
| author | Wang, Di Zhang, Jing Xu, Minqiang Liu, Lin Wang, Dongsheng Gao, Erzhong Han, Chengxi Guo, Haonan Du, Bo Tao, Dacheng Zhang, Liangpei |
| author_facet | Wang, Di Zhang, Jing Xu, Minqiang Liu, Lin Wang, Dongsheng Gao, Erzhong Han, Chengxi Guo, Haonan Du, Bo Tao, Dacheng Zhang, Liangpei |
| contents | Foundation models have reshaped the landscape of Remote Sensing (RS) by enhancing various image interpretation tasks. Pretraining is an active research topic, encompassing supervised and self-supervised learning methods to initialize model weights effectively. However, transferring the pretrained models to downstream tasks may encounter task discrepancy due to their formulation of pretraining as image classification or object discrimination tasks. In this study, we explore the Multi-Task Pretraining (MTP) paradigm for RS foundation models to address this issue. Using a shared encoder and task-specific decoder architecture, we conduct multi-task supervised pretraining on the SAMRS dataset, encompassing semantic segmentation, instance segmentation, and rotated object detection. MTP supports both convolutional neural networks and vision transformer foundation models with over 300 million parameters. The pretrained models are finetuned on various RS downstream tasks, such as scene classification, horizontal and rotated object detection, semantic segmentation, and change detection. Extensive experiments across 14 datasets demonstrate the superiority of our models over existing ones of similar size and their competitive performance compared to larger state-of-the-art models, thus validating the effectiveness of MTP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_13430 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining Wang, Di Zhang, Jing Xu, Minqiang Liu, Lin Wang, Dongsheng Gao, Erzhong Han, Chengxi Guo, Haonan Du, Bo Tao, Dacheng Zhang, Liangpei Computer Vision and Pattern Recognition Foundation models have reshaped the landscape of Remote Sensing (RS) by enhancing various image interpretation tasks. Pretraining is an active research topic, encompassing supervised and self-supervised learning methods to initialize model weights effectively. However, transferring the pretrained models to downstream tasks may encounter task discrepancy due to their formulation of pretraining as image classification or object discrimination tasks. In this study, we explore the Multi-Task Pretraining (MTP) paradigm for RS foundation models to address this issue. Using a shared encoder and task-specific decoder architecture, we conduct multi-task supervised pretraining on the SAMRS dataset, encompassing semantic segmentation, instance segmentation, and rotated object detection. MTP supports both convolutional neural networks and vision transformer foundation models with over 300 million parameters. The pretrained models are finetuned on various RS downstream tasks, such as scene classification, horizontal and rotated object detection, semantic segmentation, and change detection. Extensive experiments across 14 datasets demonstrate the superiority of our models over existing ones of similar size and their competitive performance compared to larger state-of-the-art models, thus validating the effectiveness of MTP. |
| title | MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.13430 |