Ensemble methods are generally regarded to be better than a single model if the base learners are deemed to be "accurate" and "diverse." Here we investigate a semi-supervised ensemble learning strategy to produce generalizable blind image quality assessment models. We train a multi-head convolutional network for quality prediction by maximizing the accuracy of the ensemble (as well as the base learners) on labeled data, and the disagreement (i.e., diversity) among them on unlabeled data, both implemented by the fidelity loss. We conduct extensive experiments to demonstrate the advantages of employing unlabeled data for BIQA, especially in model generalization and failure identification.

翻译：如果基本学习者被视为“准确”和“不同”的,通常认为综合方法比单一模型好。 我们在这里调查一个半监督的混合学习战略,以产生可通用的盲人图像质量评估模型。 我们训练一个多头革命性质量预测网络,在标签数据上尽可能提高组合(以及基本学习者)的准确性,并尽可能提高它们之间在无标签数据上的分歧(即多样性),两者都是由忠诚损失造成的。 我们进行了广泛的实验,以展示使用未标签数据对BIQA的优势,特别是在模型的概括化和故障识别方面。