mlsanityData to 7 Oct 2026

DroneIQA-VLE: Multi-Task Drone Image Quality Assessment via Vision-Language Ensemble

arXiv 2607.00416 ↗First posted 1 Jul 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 18 references that are in the map. First posted on arXiv 1 Jul 2026.

Builds on

14 of 18 references.

References · 14

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,127
  4. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 276
  5. 2018The Unmanned Aerial Vehicle Benchmark: Object Detection and Trackingcited by 207
  6. 2022A Deep Learning based No-reference Quality Assessment Model for UGC Videoscited by 128
  7. 2018Vision Meets Drones: A Challengecited by 80
  8. 2021Blind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion and Iterative Mixed Database Trainingcited by 71
  9. 2024Large Multi-modality Model Assisted AI-Generated Image Quality Assessmentcited by 24
  10. 2024Enhancing Blind Video Quality Assessment with Rich Quality-aware Featurescited by 19
  11. 2022Deep Neural Network for Blind Visual Quality Assessment of 4K Contentcited by 14
  12. 2024Assessing UHD Image Quality from Aesthetics, Distortions, and Saliencycited by 9
2 more
  1. 2025VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learningcited by 9
  2. 2025Efficient Face Image Quality Assessment via Self-training and Knowledge Distillationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System
  2. 2026UAVBench and UAVIT-1M: Benchmarking and Enhancing MLLMs for Low-Altitude UAV Vision-Language Understanding
  3. 2026DroneGround: Open-Vocabulary Drone Payload Characterization Using Synthetic Data and Grounded Vision-Language Models
  4. 2026Memory-Augmented Multimodal Large Language Models for Small Object Understanding in Streaming Aerial Videos
  5. 2026SkyVLaM: Multimodal Large Language Model for UAV Video Understanding in Remote Sensing
  6. 2025Towards Accurate UAV Image Perception: Guiding Vision-Language Models with Stronger Task Prompts
  7. 2025VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments
  8. 2025AirCopBench: A Benchmark for Multi-drone Collaborative Embodied Perception and Reasoning