Full-reference (FR) image quality assessment (IQA) evaluates the visual quality of a distorted image by measuring its perceptual difference with pristine-quality reference, and has been widely used in low-level vision tasks. Pairwise labeled data with mean opinion score (MOS) are required in training FR-IQA model, but is time-consuming and cumbersome to collect. In contrast, unlabeled data can be easily collected from an image degradation or restoration process, making it encouraging to exploit unlabeled training data to boost FR-IQA performance. Moreover, due to the distribution inconsistency between labeled and unlabeled data, outliers may occur in unlabeled data, further increasing the training difficulty. In this paper, we suggest to incorporate semi-supervised and positive-unlabeled (PU) learning for exploiting unlabeled data while mitigating the adverse effect of outliers. Particularly, by treating all labeled data as positive samples, PU learning is leveraged to identify negative samples (i.e., outliers) from unlabeled data. Semi-supervised learning (SSL) is further deployed to exploit positive unlabeled data by dynamically generating pseudo-MOS. We adopt a dual-branch network including reference and distortion branches. Furthermore, spatial attention is introduced in the reference branch to concentrate more on the informative regions, and sliced Wasserstein distance is used for robust difference map computation to address the misalignment issues caused by images recovered by GAN models. Extensive experiments show that our method performs favorably against state-of-the-arts on the benchmark datasets PIPAL, KADID-10k, TID2013, LIVE and CSIQ.

翻译：全参照图像质量评估(IQA) 测量了被扭曲图像的视觉质量,测量了它与原始质量参考值之间的视觉差异,并被广泛用于低层次的视觉任务。在培训 FR-IQA 模型时,需要使用带有中度意见评分(MOS) 的贴字数据,但这种数据耗时繁琐。相反,通过图像降解或恢复过程很容易地收集未贴标签的数据,从而鼓励利用未贴标签的培训数据来提升 FR-IQA 的性能。此外,由于标签和未贴标签数据之间的分布不一致,在未贴标签的数据中可能会出现外端数据,从而进一步增加培训难度。 在本文中,我们建议采用半超值和正值评分的标签标签标签数据,通过在不贴标签的直径比值的图像参考值中进一步运用了S-S-Curverical QAL 数据库, 并且通过在动态的服务器服务器上进一步运用了我们的数据, 正在使用双级的S-label-ar-ar-ar-al-arrideal-deal-deal-de-de-deal-deal-deal-de-de-deal-de-deal-deal-deal-deal-delegal-de laut the we disal-s