DELNet: Continuous All-in-One Weather Removal via Dynamic Expert Library
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911408998842368 |
|---|---|
| author | Liu, Shihong Zuo, Kun Xiao, Hanguang |
| author_facet | Liu, Shihong Zuo, Kun Xiao, Hanguang |
| contents | All-in-one weather image restoration methods are valuable in practice but depend on pre-collected data and require retraining for unseen degradations, leading to high cost. We propose DELNet, a continual learning framework for weather image restoration. DELNet integrates a judging valve that measures task similarity to distinguish new from known tasks, and a dynamic expert library that stores experts trained on different degradations. For new tasks, the valve selects top-k experts for knowledge transfer while adding new experts to capture task-specific features; for known tasks, the corresponding experts are directly reused. This design enables continuous optimization without retraining existing models. Experiments on OTS, Rain100H, and Snow100K demonstrate that DELNet surpasses state-of-the-art continual learning methods, achieving PSNR gains of 16\%, 11\%, and 12\%, respectively. These results highlight the effectiveness, robustness, and efficiency of DELNet, which reduces retraining cost and enables practical deployment in real-world scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22573 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DELNet: Continuous All-in-One Weather Removal via Dynamic Expert Library Liu, Shihong Zuo, Kun Xiao, Hanguang Computer Vision and Pattern Recognition All-in-one weather image restoration methods are valuable in practice but depend on pre-collected data and require retraining for unseen degradations, leading to high cost. We propose DELNet, a continual learning framework for weather image restoration. DELNet integrates a judging valve that measures task similarity to distinguish new from known tasks, and a dynamic expert library that stores experts trained on different degradations. For new tasks, the valve selects top-k experts for knowledge transfer while adding new experts to capture task-specific features; for known tasks, the corresponding experts are directly reused. This design enables continuous optimization without retraining existing models. Experiments on OTS, Rain100H, and Snow100K demonstrate that DELNet surpasses state-of-the-art continual learning methods, achieving PSNR gains of 16\%, 11\%, and 12\%, respectively. These results highlight the effectiveness, robustness, and efficiency of DELNet, which reduces retraining cost and enables practical deployment in real-world scenarios. |
| title | DELNet: Continuous All-in-One Weather Removal via Dynamic Expert Library |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.22573 |