This repo hosts the checkpoint of Florence-2-larged trained on DOTA-v1.0 with LMMRotate. More checkpoint for aerial detection with LMMRotate in our paper can be found in this repo.

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.

Downloading Guide

You can download with your web browser on the file page.

We recommand downloading in terminal using huggingface-cli (pip install --upgrade huggingface_cli). You can refer to the document for more usages.

# Set Huggingface Mirror for Chinese users (if required):
export HF_ENDPOINT=https://hf-mirror.com 
# Download a certain checkpoint:
huggingface-cli download Qingyun/Florence-2-large-DOTA-v1.0-lmmrotate --repo-type model --local-dir checkpoint/Florence-2-large-DOTA-v1.0-lmmrotate/
# If any error (such as network error) interrupts the downloading, you just need to execute the same command, the latest huggingface_hub will resume downloading.

Detection Performance

Cite

LMMRotate paper:

@article{li2025lmmrotate,
  title={A Simple Aerial Detection Baseline of Multimodal Language Models},
  author={Li, Qingyun and Chen, Yushi and Shu, Xinya and Chen, Dong and He, Xin and Yu Yi and Yang, Xue },
  journal={arXiv preprint arXiv:2501.09720},
  year={2025}
}