In this paper, we present a simple yet effective continual learning method for blind image quality assessment (BIQA) with improved quality prediction accuracy, plasticity-stability trade-off, and task-order/-length robustness. The key step in our approach is to freeze all convolution filters of a pre-trained deep neural network (DNN) for an explicit promise of stability, and learn task-specific normalization parameters for plasticity. We assign each new IQA dataset (i.e., task) a prediction head, and load the corresponding normalization parameters to produce a quality score. The final quality estimate is computed by black a weighted summation of predictions from all heads with a lightweight $K$-means gating mechanism. Extensive experiments on six IQA datasets demonstrate the advantages of the proposed method in comparison to previous training techniques for BIQA.

翻译：本文提出了一种简单而有效的持续学习方法，用于盲图像质量评估，该方法在提高质量预测精度的同时，实现了可塑性-稳定性权衡与任务顺序/长度的鲁棒性。我们方法的核心步骤是冻结预训练深度神经网络的所有卷积滤波器以保证稳定性，并学习任务特定的归一化参数以实现可塑性。我们为每个新的IQA数据集（即任务）分配一个预测头，并加载相应的归一化参数以生成质量分数。最终质量估计通过一个轻量级的K均值门控机制对所有预测头的输出进行加权求和计算。在六个IQA数据集上的大量实验表明，所提方法相对于先前的BIQA训练技术具有明显优势。