Scientific Image Quality Assessment via Multi-modal Retrieval-Augmented Generation
cs.CV, cs.CL
Submitted: 2026-09-17
Updated: 2026-09-17
Code: https://github.com/qdrant/qdrant
License: http://creativecommons.org/licenses/by/4.0/
The gist: This paper proposes a Retrieval-Augmented Generation (RAG) framework for scientific image quality assessment, designed to simultaneously address both the understanding track (SIQA-U) and the scoring
Terminology
Abstract
This paper proposes a Retrieval-Augmented Generation (RAG) framework for scientific image quality assessment, designed to simultaneously address both the understanding track (SIQA-U) and the scoring track (SIQA-S) of the SIQA challenge. We construct a multimodal index that integrates textual semantics with fine-grained visual features, and develop a multi-route retrieval and fusion mechanism to provide large language models with highly relevant reference cases, thereby enhancing their capability to evaluate complex scientific images. Experimental results demonstrate that the proposed framework effectively aligns with the judgment criteria of human experts. Ultimately, our method achieves 1st place in the SIQA-U track of the SIQA challenge at the ICME 2026 Grand Challenges.
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models