发表机构
University of Edinburgh; Baidu Inc.; Tsinghua University; Harbin Institute of Technology, Shenzhen（爱丁堡大学; 百度公司; 清华大学; 哈尔滨工业大学（深圳））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出RwF，一种滤波器级连续图像恢复框架，通过参数空间积分梯度定位关键滤波器，生成任务特定滤波器，避免遗忘并以更少参数达到竞争性恢复质量。
AI 中文摘要
将图像恢复模型适应到一系列新任务而不重新访问过去的数据，由于灾难性遗忘仍然具有挑战性。在这项工作中，我们提出了不遗忘的恢复（RwF），一种基于关键观察的滤波器级连续图像恢复适应框架：任务特定知识集中在少量滤波器子集中，并且可以与重建一般内容的滤波器分离。RwF首先执行参数空间积分梯度归因，以由粗到细的方式定位退化关键滤波器。然后，它通过使用紧凑的因子化低秩变换从滤波器库生成任务特定滤波器来适应新任务，进一步通过跨任务注意力和原型对比学习增强，最后仅将它们在定位位置组装回来。在六个恢复任务上的实验表明，RwF有效避免遗忘，并实现了与具有完整数据访问的全能方法相当的恢复质量，并且以约10倍更少的额外参数优于LoRA风格的适应。代码可在该HTTPS URL获得。
英文摘要
Adapting image restoration models to a stream of new tasks without revisiting past data remains challenging due to catastrophic forgetting. In this work, we propose Restoring without Forgetting (RwF), a filter-level continual adaptation framework for image restoration built upon a critical observation: task-specific knowledge is centered in a small subset of filters and can be separated from those reconstructing general content. RwF first performs parameter-space integrated gradients attribution to localize degradation-critical filters in a coarse-to-fine manner. It then adapts to new tasks by generating task-specific filters from a filter bank using compact factorized low-rank transformations, further augmented with cross-task attention and prototypical contrastive learning, and lastly assembles them back only at localized positions. Experiments on six restoration tasks show that RwF effectively avoids forgetting and achieves competitive restoration quality against all-in-one methods that have full data access, and outperforms LoRA-style adaptation with $\sim$10$\times$ fewer additional parameters. Code is available at https://github.com/funkdub/Restoring-without-Forgetting.
