Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network Structure
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.
Code (1)
Tasks
AllContinual LearningImage RestorationIncremental LearningKnowledge DistillationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention
Semantic segmentation's performance is often compromised when applied to unlabeled adverse weather conditions. Unsupervised domain adaptation is a potential approach to enhancing the model's adaptability and robustness t…
Domain AdaptationMulti-target Domain AdaptationSemantic SegmentationUnsupervised Domain AdaptationLearning Multiple Adverse Weather Removal via Two-Stage Knowledge Learning and Multi-Contrastive Regularization: Toward a Unified Model
In this paper, an ill-posed problem of multiple adverse weather removal is investigated. Our goal is to train a model with a 'unified' architecture and only one set of pretrained weights that can tackle multiple type…
Transfer LearningContinuous Adverse Weather Removal via Degradation-Aware Distillation
All-in-one models for adverse weather removal aim to process various degraded images using a single set of parameters, making them ideal for real-world scenarios. However, they encounter two main challenges: catastro…
Incremental LearningSemiDDM-Weather: A Semi-supervised Learning Framework for All-in-one Adverse Weather Removal
Adverse weather removal aims to restore clear vision under adverse weather conditions. Existing methods are mostly tailored for specific weather types and rely heavily on extensive labeled data. In dealing with these two…
AllDenoisingWM-MoE: Weather-aware Multi-scale Mixture-of-Experts for Blind Adverse Weather Removal
Adverse weather removal tasks like deraining, desnowing, and dehazing are usually treated as separate tasks. However, in practical autonomous driving scenarios, the type, intensity,and mixing degree of weather are unknow…
Autonomous DrivingContrastive LearningMixture-of-ExpertsRain Removal