Task-Specific Normalization for Continual Learning of Blind Image Quality Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2021
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909111104307200 |
|---|---|
| author | Zhang, Weixia Ma, Kede Zhai, Guangtao Yang, Xiaokang |
| author_facet | Zhang, Weixia Ma, Kede Zhai, Guangtao Yang, Xiaokang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2107_13429 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Task-Specific Normalization for Continual Learning of Blind Image Quality Models Zhang, Weixia Ma, Kede Zhai, Guangtao Yang, Xiaokang Computer Vision and Pattern Recognition 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. |
| title | Task-Specific Normalization for Continual Learning of Blind Image Quality Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2107.13429 |