LIRA: Lifelong Image Restoration from Unknown Blended Distortions
This addresses the issue of forgetting in image restoration for blended distortions, which is incremental as it builds on existing expert models with a neural growing strategy.
The paper tackles the problem of catastrophic forgetting in image restoration networks when handling blended distortions, proposing a lifelong learning approach that achieves state-of-the-art performance in PSNR/SSIM metrics while maintaining old expertise.
Most existing image restoration networks are designed in a disposable way and catastrophically forget previously learned distortions when trained on a new distortion removal task. To alleviate this problem, we raise the novel lifelong image restoration problem for blended distortions. We first design a base fork-join model in which multiple pre-trained expert models specializing in individual distortion removal task work cooperatively and adaptively to handle blended distortions. When the input is degraded by a new distortion, inspired by adult neurogenesis in human memory system, we develop a neural growing strategy where the previously trained model can incorporate a new expert branch and continually accumulate new knowledge without interfering with learned knowledge. Experimental results show that the proposed approach can not only achieve state-of-the-art performance on blended distortions removal tasks in both PSNR/SSIM metrics, but also maintain old expertise while learning new restoration tasks.