Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.08168 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929740229640192 |
|---|---|
| author | Ma, Zhiming Xiao, Xiayang Dong, Sihao Wang, Peidong Wang, HaiPeng Pan, Qingyun |
| author_facet | Ma, Zhiming Xiao, Xiayang Dong, Sihao Wang, Peidong Wang, HaiPeng Pan, Qingyun |
| contents | As a powerful all-weather Earth observation tool, synthetic aperture radar (SAR) remote sensing enables critical military reconnaissance, maritime surveillance, and infrastructure monitoring. Although Vision language models (VLMs) have made remarkable progress in natural language processing and image understanding, their applications remain limited in professional domains due to insufficient domain expertise. This paper innovatively proposes the first large-scale multimodal dialogue dataset for SAR images, named SARChat-2M, which contains approximately 2 million high-quality image-text pairs, encompasses diverse scenarios with detailed target annotations. This dataset not only supports several key tasks such as visual understanding and object detection tasks, but also has unique innovative aspects: this study develop a visual-language dataset and benchmark for the SAR domain, enabling and evaluating VLMs' capabilities in SAR image interpretation, which provides a paradigmatic framework for constructing multimodal datasets across various remote sensing vertical domains. Through experiments on 16 mainstream VLMs, the effectiveness of the dataset has been fully verified. The project will be released at https://github.com/JimmyMa99/SARChat. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_08168 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SARChat-Bench-2M: A Multi-Task Vision-Language Benchmark for SAR Image Interpretation Ma, Zhiming Xiao, Xiayang Dong, Sihao Wang, Peidong Wang, HaiPeng Pan, Qingyun Computation and Language As a powerful all-weather Earth observation tool, synthetic aperture radar (SAR) remote sensing enables critical military reconnaissance, maritime surveillance, and infrastructure monitoring. Although Vision language models (VLMs) have made remarkable progress in natural language processing and image understanding, their applications remain limited in professional domains due to insufficient domain expertise. This paper innovatively proposes the first large-scale multimodal dialogue dataset for SAR images, named SARChat-2M, which contains approximately 2 million high-quality image-text pairs, encompasses diverse scenarios with detailed target annotations. This dataset not only supports several key tasks such as visual understanding and object detection tasks, but also has unique innovative aspects: this study develop a visual-language dataset and benchmark for the SAR domain, enabling and evaluating VLMs' capabilities in SAR image interpretation, which provides a paradigmatic framework for constructing multimodal datasets across various remote sensing vertical domains. Through experiments on 16 mainstream VLMs, the effectiveness of the dataset has been fully verified. The project will be released at https://github.com/JimmyMa99/SARChat. |
| title | SARChat-Bench-2M: A Multi-Task Vision-Language Benchmark for SAR Image Interpretation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.08168 |