DroneIQA-VLE: Multi-Task Drone Image Quality Assessment via Vision-Language Ensemble
Abstract
We present DroneIQA-VLE, our solution to the ICME 2026 Drone-IQA Grand Challenge on Target-aware Image Quality Assessment for Low-altitude UAV Images. The framework jointly predicts global, target, and background quality scores by ensembling two complementary pipelines: (1) SigLIP2 vision encoders with multi-task regression heads, and (2) a LoRA-adapted Qwen3.5-9B multimodal large language model for quality score regression. The final global quality prediction is obtained by arithmetically averaging the outputs of both pipelines. Our method achieves 2nd place in the challenge, demonstrating its effectiveness. The code is available at https://github.com/sunwei925/DroneIQA-VLE.
Cite
@article{arxiv.2607.00416,
title = {DroneIQA-VLE: Multi-Task Drone Image Quality Assessment via Vision-Language Ensemble},
author = {Wei Sun and Weixia Zhang and Hongjian Zhan and Mingkai Lu and Yixuan Gao and Guangtao Zhai},
journal= {arXiv preprint arXiv:2607.00416},
year = {2026}
}
Comments
The model achieves 2nd place in ICME 2026 Drone-IQA Grand Challenge on Target-aware Image Quality Assessment for Low-altitude UAV Images