Building Reasonable Inference for Vision-Language Models in Blind Image Quality Assessment
构建合理的视觉-语言模型推理以实现盲图像质量评估
机构 * Graduate School of Informatics, Kyoto University(京都大学信息学研究生院)
专题命中 其他推理 :reasoning(abstract)
AI总结 本文提出一种两阶段调优方法,通过分离视觉感知与质量推断,提升视觉-语言模型在盲图像质量评估中的推理稳定性与可靠性。
Comments Accepted to the ICONIP (International Conference on Neural Information Processing), 2025
Journal ref Building Reasonable Inference for Vision-Language Models in Blind Image Quality Assessment. In: Taniguchi, T., et al. Neural Information Processing. ICONIP 2025. Lecture Notes in Computer Science, vol 16310. Springer, Singapore