SciQNet：面向科学图像质量评估的两阶段多模态适配框架

中文摘要 AI 辅助

科学图像对于传递实验观测、定量证据和概念知识至关重要。与自然图像不同，其质量取决于视觉清晰度和科学信息量，评估颇具挑战。本研究提出SciQNet，一种用于科学图像质量评估的两阶段多模态适配框架：第一阶段对科学文档图像进行领域自适应预训练，第二阶段采用联合评分与理解监督开展任务特定微调。针对评分导向的监督，将指令调优与从评级词logits导出的Huber损失相结合；理解导向的监督则表述为多项选择视觉问答。实验表明，在评估的预训练比例中，使用领域自适应数据的40%分层子集性能最佳，提示预训练数据相关性可能与规模同等重要。最终模型取得SIQA-S得分92.21、SIQA-U得分47.38，综合得分69.80。本研究为ICME 2026科学图像质量评估挑战赛提供解决方案，在评分赛道中排名第2。

英文摘要

Scientific images are essential for communicating experimental observations, quantitative evidence and conceptual knowledge. Unlike natural images, their quality depends on both visual clarity and scientific informativeness, making assessment challenging. In this work, we present SciQNet, a two-stage multimodal adaptation framework for scientific image quality assessment. The first stage performs domain-adaptive pretraining on scientific document images and the second stage conducts task-specific fine-tuning with joint scoring and understanding supervision. For scoring-oriented supervision, we combine instruction tuning with a Huber loss derived from rating-word logits, while understanding-oriented supervision is formulated as multiple-choice visual question answering. Experiments show that using a 40% stratified subset of the domain-adaptive data gives the best performance among the evaluated pretraining fractions, suggesting that pretraining-data relevance may be as important as pretraining-data scale. The final model achieves an SIQA-S score of 92.21, an SIQA-U score of 47.38 and a combined score of 69.80. This work presents our solution to the ICME 2026 Scientific Image Quality Assessment Challenge, which ranked 2nd in the scoring track.

发表机构

• Universiti Malaya（马来亚大学）
• Universiti Tunku Abdul Rahman（拉曼大学）
• National University of Singapore（新加坡国立大学）

机构由 AI 辅助整理，请以论文原文为准。