Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,45 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- Qingyun/lmmrotate-sft-data
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
base_model:
|
| 8 |
+
- microsoft/Florence-2-large
|
| 9 |
+
pipeline_tag: image-text-to-text
|
| 10 |
+
tags:
|
| 11 |
+
- aerial
|
| 12 |
+
- geoscience
|
| 13 |
+
- remotesensing
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<p align="center">
|
| 17 |
+
<h1 align="center">LMMRotate 🎮: A Simple Aerial Detection Baseline of Multimodal Language Models</h1>
|
| 18 |
+
<p align="center">
|
| 19 |
+
<a href='https://scholar.google.com/citations?hl=en&user=TvsTun4AAAAJ' style='text-decoration: none' >Qingyun Li</a><sup></sup> 
|
| 20 |
+
<a href='https://scholar.google.com/citations?user=A39S7JgAAAAJ&hl=en' style='text-decoration: none' >Yushi Chen</a><sup></sup> 
|
| 21 |
+
<a href='https://www.researchgate.net/profile/Shu-Xinya' style='text-decoration: none' >Xinya Shu</a><sup></sup> 
|
| 22 |
+
<a href='https://scholar.google.com/citations?hl=en&user=UzPtYnQAAAAJ' style='text-decoration: none' >Dong Chen</a><sup></sup> 
|
| 23 |
+
<a href='https://scholar.google.com/citations?hl=en&user=WQgE8l8AAAAJ' style='text-decoration: none' >Xin He</a><sup></sup> 
|
| 24 |
+
<a href='https://scholar.google.com/citations?user=OYtSc4AAAAAJ&hl=en' style='text-decoration: none' >Yi Yu</a><sup></sup> 
|
| 25 |
+
<a href='https://yangxue0827.github.io/' style='text-decoration: none' >Xue Yang</a><sup></sup> 
|
| 26 |
+
<p align='center'>
|
| 27 |
+
If you find our work helpful, please consider giving us a ⭐!
|
| 28 |
+
</p>
|
| 29 |
+
</p>
|
| 30 |
+
</p>
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
- ArXiv Paper: https://arxiv.org/abs/2501.09720
|
| 34 |
+
- GitHub Repo: https://github.com/Li-Qingyun/mllm-mmrotate
|
| 35 |
+
- HuggingFace Page: https://huggingface.co/collections/Qingyun/lmmrotate-6780cabaf49c4e705023b8df
|
| 36 |
+
|
| 37 |
+
This repo hosts all the available checkpoints of Florence-2 trained for aerial detection with LMMRotate in [our paper](https://arxiv.org/abs/2501.09720).
|
| 38 |
+
|
| 39 |
+
LMMRotate is a technical practice to fine-tune Large Multimodal language Models for oriented object detection as in MMRotate and hosts the official implementation of the paper: A Simple Aerial Detection Baseline of Multimodal Language Models.
|
| 40 |
+
|
| 41 |
+
<img src="https://github.com/user-attachments/assets/d34e4c0c-9e04-446e-a511-2e7005e32074" alt="framework" width="100%" />
|
| 42 |
+
|
| 43 |
+
## Detection Performance
|
| 44 |
+
|
| 45 |
+
|