Task-Specific Normalization for Continual Learning of Blind Image Quality Models
This work addresses the challenge of adapting BIQA models to new datasets without forgetting previous knowledge, which is incremental as it builds on existing continual learning techniques for a specific domain.
The paper tackles the problem of continual learning for blind image quality assessment (BIQA) by introducing a method that freezes convolution filters for stability and learns task-specific normalization parameters for plasticity, resulting in improved prediction accuracy, better plasticity-stability trade-off, and enhanced robustness to task order and length across six IQA datasets.
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.