无需训练，用大模型实现精准图像质量评估。
Dog-IQA: Standard-guided Zero-shot MLLM for Mix-grained Image Quality Assessment
- 模仿人类专家评分，结合标准与多模态先验知识。
- 跨数据集测试中表现优于现有无训练方法。
- 适合需要快速评估图像质量的场景。
图像质量评估（IQA）是计算机视觉领域几乎所有模型性能的黄金标准。然而，现有方法仍存在分布外泛化能力差和训练成本高的问题。为此，我们提出 Dog-IQA，一种基于标准引导的零样本混合粒度 IQA 方法，无需训练且利用多模态大语言模型（MLLM）的强先验知识。为获得与人类一致的评分，我们设计了模拟人类专家的 MLLM 推理流程：首先，通过特定标准客观评分，利用 MLLM 的行为模式并减少主观因素影响；其次，综合局部语义对象与整体图像输入，聚合其得分，融合局部与全局信息。在跨数据集场景下，Dog-IQA 在无训练方法中达到领先性能，在有训练方法中也表现相当。代码将开源于 https://github.com/Kai-Liu001/Dog-IQA。
原文摘要 · Abstract (English)
Image quality assessment (IQA) serves as the golden standard for all models' performance in nearly all computer vision fields. However, it still suffers from poor out-of-distribution generalization ability and expensive training costs. To address these problems, we propose Dog-IQA, a standard-guided zero-shot mix-grained IQA method, which is training-free and utilizes the exceptional prior knowledge of multimodal large language models (MLLMs). To obtain accurate IQA scores, namely scores consistent with humans, we design an MLLM-based inference pipeline that imitates human experts. In detail, Dog-IQA applies two techniques. First, Dog-IQA objectively scores with specific standards that utilize MLLM's behavior pattern and minimize the influence of subjective factors. Second, Dog-IQA comprehensively takes local semantic objects and the whole image as input and aggregates their scores, leveraging local and global information. Our proposed Dog-IQA achieves state-of-the-art (SOTA) performance compared with training-free methods, and competitive performance compared with training-based methods in cross-dataset scenarios. Our code will be available at https://github.com/Kai-Liu001/Dog-IQA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。