LIQA: Lifelong Blind Image Quality Assessment
Jianzhao Liu, Wei Zhou, Jiahua Xu, Xin Li, Shukun An, Zhibo Chen

TL;DR
The paper introduces LIQA, a lifelong learning approach for blind image quality assessment that adaptively learns new distortions without forgetting previous ones, suitable for real-world applications.
Contribution
LIQA is the first lifelong BIQA method that mitigates catastrophic forgetting and learns continuously from new distortions without access to past training data.
Findings
LIQA effectively handles continuous distortion shifts.
The model maintains stable performance over long task sequences.
It outperforms existing BIQA methods in lifelong learning scenarios.
Abstract
Existing blind image quality assessment (BIQA) methods are mostly designed in a disposable way and cannot evolve with unseen distortions adaptively, which greatly limits the deployment and application of BIQA models in real-world scenarios. To address this problem, we propose a novel Lifelong blind Image Quality Assessment (LIQA) approach, targeting to achieve the lifelong learning of BIQA. Without accessing to previous training data, our proposed LIQA can not only learn new distortions, but also mitigate the catastrophic forgetting of seen distortions. Specifically, we adopt the Split-and-Merge distillation strategy to train a single-head network that makes task-agnostic predictions. In the split stage, we first employ a distortion-specific generator to obtain the pseudo features of each seen distortion. Then, we use an auxiliary multi-head regression network to generate the predicted…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage and Video Quality Assessment · Advanced Image Fusion Techniques · Visual Attention and Saliency Detection
