Vision-Language Model Purified Semi-Supervised Semantic Segmentation for Remote Sensing Images
Paper • 2602.00202 • Published
Image Segmentation
Transformers
English
Chinese
remote sensing
vision language model
semi-supervised
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("fluorites/SemiEarth", dtype="auto")Quick Links
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}}
}
Model tree for fluorites/SemiEarth
Base model
Qwen/Qwen-VL
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="fluorites/SemiEarth")