基于统一网络结构上知识重放的持续一体化恶劣天气去除
Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network Structure
AI总结：
针对现有恶劣天气去除方法无法应对增量学习的问题，研究提出搭载主成分投影与知识蒸馏的知识重放持续学习框架，在统一网络中实现多退化知识共享积累，性能比肩现有专用或联合训练方法。
摘要：
在实际应用中，恶劣天气导致的图像退化往往十分复杂，且会随日期、季节对应的不同天气状况发生变化。真实环境中的系统会不断遭遇此前未观测到的恶劣天气条件，因此恶劣天气去除模型需要具备从逐步收集的、反映各类退化类型的数据中持续学习的能力。现有的单类或多类恶劣天气去除方法主要针对静态学习范式设计，这类范式假设所有待处理的退化类型数据都能在单阶段学习过程开始前一次性完整收集，因此无法直接应对增量学习需求。为解决这一问题，我们率先开展了更贴近实际应用场景的持续一体化恶劣天气去除任务研究。具体而言，我们提出了一种在统一网络结构上搭载高效知识重放（KR）的新型持续学习框架。所提出的KR技术配备主成分投影和高效知识蒸馏机制，是专为一体化天气去除任务定制的。它考虑了持续学习中多退化图像恢复任务的特性，不同退化的知识可以在统一网络结构中实现共享与积累。大量实验结果证明了所提方法应对这一挑战性任务的有效性，其性能与现有的专用或联合训练图像恢复方法相当。我们的代码可在https://github.com/xiaojihh/CL_all-in-one获取。
英文摘要：
In real-world applications, image degeneration caused by adverse weather is always complex and changes with different weather conditions from days and seasons. Systems in real-world environments constantly encounter adverse weather conditions that are not previously observed. Therefore, it practically requires adverse weather removal models to continually learn from incrementally collected data reflecting various degeneration types. Existing adverse weather removal approaches, for either single or multiple adverse weathers, are mainly designed for a static learning paradigm, which assumes that the data of all types of degenerations to handle can be finely collected at one time before a single-phase learning process. They thus cannot directly handle the incremental learning requirements. To address this issue, we made the earliest effort to investigate the continual all-in-one adverse weather removal task, in a setting closer to real-world applications. Specifically, we develop a novel continual learning framework with effective knowledge replay (KR) on a unified network structure. Equipped with a principal component projection and an effective knowledge distillation mechanism, the proposed KR techniques are tailored for the all-in-one weather removal task. It considers the characteristics of the image restoration task with multiple degenerations in continual learning, and the knowledge for different degenerations can be shared and accumulated in the unified network structure. Extensive experimental results demonstrate the effectiveness of the proposed method to deal with this challenging task, which performs competitively to existing dedicated or joint training image restoration methods. Our code is available at https://github.com/xiaojihh/CL_all-in-one.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
