Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.20776 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908748067373056 |
|---|---|
| author | Hu, Huiyang Wang, Peijin Feng, Yingchao Wei, Kaiwen Yin, Wenxin Diao, Wenhui Wang, Mengyu Bi, Hanbo Kang, Kaiyue Ling, Tong Fu, Kun Sun, Xian |
| author_facet | Hu, Huiyang Wang, Peijin Feng, Yingchao Wei, Kaiwen Yin, Wenxin Diao, Wenhui Wang, Mengyu Bi, Hanbo Kang, Kaiyue Ling, Tong Fu, Kun Sun, Xian |
| contents | Remote sensing (RS) images from multiple modalities and platforms exhibit diverse details due to differences in sensor characteristics and imaging perspectives. Existing vision-language research in RS largely relies on relatively homogeneous data sources. Moreover, they still remain limited to conventional visual perception tasks such as classification or captioning. As a result, these methods fail to serve as a unified and standalone framework capable of effectively handling RS imagery from diverse sources in real-world applications. To address these issues, we propose RingMo-Agent, a model designed to handle multi-modal and multi-platform data that performs perception and reasoning tasks based on user textual instructions. Compared with existing models, RingMo-Agent 1) is supported by a large-scale vision-language dataset named RS-VL3M, comprising over 3 million image-text pairs, spanning optical, SAR, and infrared (IR) modalities collected from both satellite and UAV platforms, covering perception and challenging reasoning tasks; 2) learns modality adaptive representations by incorporating separated embedding layers to construct isolated features for heterogeneous modalities and reduce cross-modal interference; 3) unifies task modeling by introducing task-specific tokens and employing a token-based high-dimensional hidden state decoding mechanism designed for long-horizon spatial tasks. Extensive experiments on various RS vision-language tasks demonstrate that RingMo-Agent not only proves effective in both visual understanding and sophisticated analytical tasks, but also exhibits strong generalizability across different platforms and sensing modalities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_20776 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RingMo-Agent: A Unified Remote Sensing Foundation Model for Multi-Platform and Multi-Modal Reasoning Hu, Huiyang Wang, Peijin Feng, Yingchao Wei, Kaiwen Yin, Wenxin Diao, Wenhui Wang, Mengyu Bi, Hanbo Kang, Kaiyue Ling, Tong Fu, Kun Sun, Xian Computer Vision and Pattern Recognition Remote sensing (RS) images from multiple modalities and platforms exhibit diverse details due to differences in sensor characteristics and imaging perspectives. Existing vision-language research in RS largely relies on relatively homogeneous data sources. Moreover, they still remain limited to conventional visual perception tasks such as classification or captioning. As a result, these methods fail to serve as a unified and standalone framework capable of effectively handling RS imagery from diverse sources in real-world applications. To address these issues, we propose RingMo-Agent, a model designed to handle multi-modal and multi-platform data that performs perception and reasoning tasks based on user textual instructions. Compared with existing models, RingMo-Agent 1) is supported by a large-scale vision-language dataset named RS-VL3M, comprising over 3 million image-text pairs, spanning optical, SAR, and infrared (IR) modalities collected from both satellite and UAV platforms, covering perception and challenging reasoning tasks; 2) learns modality adaptive representations by incorporating separated embedding layers to construct isolated features for heterogeneous modalities and reduce cross-modal interference; 3) unifies task modeling by introducing task-specific tokens and employing a token-based high-dimensional hidden state decoding mechanism designed for long-horizon spatial tasks. Extensive experiments on various RS vision-language tasks demonstrate that RingMo-Agent not only proves effective in both visual understanding and sophisticated analytical tasks, but also exhibits strong generalizability across different platforms and sensing modalities. |
| title | RingMo-Agent: A Unified Remote Sensing Foundation Model for Multi-Platform and Multi-Modal Reasoning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.20776 |