CLIP-driven rain perception: Adaptive deraining with pattern-aware network routing and mask-guided cross-attention

作者
Cong Guan,Osamu Yoshie
出处
期刊:Cornell University - arXiv [Cornell University]
标识
DOI:10.48550/arxiv.2506.01366
摘要

Existing deraining models process all rainy images within a single network. However, different rain patterns have significant variations, which makes it challenging for a single network to handle diverse types of raindrops and streaks. To address this limitation, we propose a novel CLIP-driven rain perception network (CLIP-RPN) that leverages CLIP to automatically perceive rain patterns by computing visual-language matching scores and adaptively routing to sub-networks to handle different rain patterns, such as varying raindrop densities, streak orientations, and rainfall intensity. CLIP-RPN establishes semantic-aware rain pattern recognition through CLIP's cross-modal visual-language alignment capabilities, enabling automatic identification of precipitation characteristics across different rain scenarios. This rain pattern awareness drives an adaptive subnetwork routing mechanism where specialized processing branches are dynamically activated based on the detected rain type, significantly enhancing the model's capacity to handle diverse rainfall conditions. Furthermore, within sub-networks of CLIP-RPN, we introduce a mask-guided cross-attention mechanism (MGCA) that predicts precise rain masks at multi-scale to facilitate contextual interactions between rainy regions and clean background areas by cross-attention. We also introduces a dynamic loss scheduling mechanism (DLS) to adaptively adjust the gradients for the optimization process of CLIP-RPN. Compared with the commonly used $l_1$ or $l_2$ loss, DLS is more compatible with the inherent dynamics of the network training process, thus achieving enhanced outcomes. Our method achieves state-of-the-art performance across multiple datasets, particularly excelling in complex mixed datasets.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
加油完成签到,获得积分10
刚刚
刚刚
嘻嘻哈哈的应助被科研小白采纳,获得10
刚刚
刚刚
1秒前
睡梦无尘完成签到 ,获得积分20
1秒前
卫大伯完成签到,获得积分10
1秒前
donkey发布了新的文献求助10
1秒前
yang发布了新的文献求助30
2秒前
2秒前
利好发布了新的文献求助10
3秒前
科目三的应助被xxkim721采纳,获得10
3秒前
3秒前
3秒前
勤奋尔丝完成签到 ,获得积分10
4秒前
4秒前
zoe完成签到,获得积分10
5秒前
小马甲的应助被ygchyh采纳,获得30
5秒前
5秒前
zzz发布了新的文献求助10
6秒前
梁xq完成签到,获得积分10
6秒前
REAL完成签到 ,获得积分10
6秒前
回忆lhy完成签到,获得积分10
6秒前
JiaYouguo发布了新的文献求助20
7秒前
于鹏完成签到,获得积分10
7秒前
8秒前
TheWinterSun完成签到,获得积分10
8秒前
沉迷学习发布了新的文献求助10
8秒前
文学痞完成签到,获得积分10
8秒前
9秒前
9秒前
nan11发布了新的文献求助10
9秒前
陶炳君发布了新的文献求助10
9秒前
10秒前
风趣犀牛完成签到,获得积分10
10秒前
wu完成签到,获得积分10
10秒前
Chen发布了新的文献求助10
11秒前
潇洒的茗茗完成签到 ,获得积分10
11秒前
AsahiKokura214完成签到,获得积分10
11秒前
12秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8187226
求助须知:如何正确求助?哪些是违规求助? 9575395
关于积分的说明 21841040
捐赠科研通 7784958
什么是DOI,文献DOI怎么找? 3434935
关于科研通互助平台的介绍 2559355
邀请新用户注册赠送积分活动 2481808