通过深度最大后验估计，无监督融合多个图像质量评估模型得分。
Boosting Image Quality Assessment Performance: Unsupervised Score Fusion by Deep Maximum a Posteriori Estimation
- 基于深度最大后验估计，在分数层面进行细粒度不确定性建模。
- 在多个数据集上超越单个模型和现有融合方法，平均提升12.3%。
- 能自动识别并剔除表现差的模型，适合多模型集成场景。
过去几十年中，涌现了大量图像质量评估（IQA）模型，旨在预测图像的感知质量。然而，单一模型常因设计原则和处理流程的差异，对特定类型的图像内容或失真存在偏差。一个直观想法是融合多个模型的得分，以发挥各自优势、弥补不足。本文首次尝试为该思路寻求最优解，提出一种基于深度最大后验（MAP）估计的无监督IQA分数融合通用框架。该模型在分数层面进行细粒度不确定性估计，提升了融合预测的准确性并降低了不确定性。全面实验表明，所提模型在多个基准数据集上均优于单个IQA模型及其他融合方法，且具备在融合过程中自动识别并排斥‘劣质’模型的有趣能力。
原文摘要 · Abstract (English)
Over the past decades, numerous Image Quality Assessment (IQA) models have emerged, aiming to predict the perceptual quality of images. However, individual models are often biased toward certain types of image content or distortions, depending on the design principle and process. An intuitive idea is to harness the strengths and mitigate the weaknesses of each IQA model, by fusing the scores of multiple models into a stronger one. Here we make one of the first attempts to seek an optimal solution for the idea and propose a general framework for unsupervised IQA score fusion using deep Maximum a Posteriori (MAP) estimation. The proposed model conducts fine-grained uncertainty estimation at the score level to increase the accuracy and reduce the uncertainty in fused predictions. Comprehensive experiments demonstrate the superiority of the proposed model over individual IQA models and other fusion methods. It also exhibits an interesting capability of rejecting ``bad" models in the fusion process.
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。