Boosting Image Quality Assessment Performance: Unsupervised Score Fusion by Deep Maximum a Posteriori Estimation
For researchers and practitioners in image quality assessment, this work provides a general method to combine multiple IQA models into a stronger one without requiring labeled data, addressing the bias of individual models.
This paper proposes an unsupervised score fusion framework for image quality assessment using deep Maximum a Posteriori estimation, which improves accuracy and reduces uncertainty by estimating fine-grained uncertainty at the score level. Experiments show the fused model outperforms individual IQA models and other fusion methods, and can reject poor-performing models.
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.