Task-Specific Normalization for Continual Learning of Blind Image Quality Models

arXiv:2107.13429v3 Announce Type: replace
Abstract: 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 …

abstract accuracy arxiv assessment blind continual convolution cs.cv filters image key normalization paper prediction quality robustness simple stability the key trade trade-off type