Image Segmentation
Transformers
English
Chinese
remote sensing
vision language model
semi-supervised
Instructions to use fluorites/SemiEarth with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fluorites/SemiEarth with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="fluorites/SemiEarth")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("fluorites/SemiEarth", dtype="auto") - Notebooks
- Google Colab
- Kaggle
metadata
license: apache-2.0
datasets:
- fluorites/SemiEarth
base_model:
- Qwen/Qwen-VL
- facebook/dinov2
pipeline_tag: image-segmentation
library_name: transformers
tags:
- remote sensing
- vision language model
- semi-supervised
language:
- en
- zh
metrics:
- miou
new_version: fluorites/SemiEarth-v1.0
Citation
If you find it useful, please consider citing:
@article{wang2026vision,
title = {Vision-Language Model Purified Semi-Supervised Semantic Segmentation for Remote Sensing Images},
author = {Wang, Shanwen and Sun, Xin and Hong, Danfeng and Zhou, Fei},
journal = {arXiv preprint arXiv:2602.00202},
year = {2026},
month = feb,
note = {Available at \url{https://arxiv.org/abs/2602.00202}}
}