卷积神经网络
魔术(望远镜)
计算机科学
变压器
利用
深度学习
人工智能
模式识别(心理学)
工程类
电气工程
物理
电压
计算机安全
量子力学
作者
Kui Jiang,Zhongyuan Wang,Chen Chen,Laizhong Cui,Chia-Wen Lin
标识
DOI:10.1145/3503161.3547760
摘要
Convolutional neural network (CNN) and Transformer have achieved great success in multimedia applications. However, little effort has been made to effectively and efficiently harmonize these two architectures to satisfy image deraining. This paper aims to unify these two architectures to take advantage of their learning merits for image deraining. In particular, the local connectivity and translation equivariance of CNN and the global aggregation ability of self-attention (SA) in Transformer are fully exploited for specific local context and global structure representations. Based on the observation that rain distribution reveals the degradation location and degree, we introduce degradation prior to help background recovery and accordingly present the association refinement deraining scheme. A novel multi-input attention module (MAM) is proposed to associate rain perturbation removal and background recovery. Moreover, we equip our model with effective depth-wise separable convolutions to learn the specific feature representations and trade off computational complexity. Extensive experiments show that our proposed method (dubbed as ELF) outperforms the state-of-the-art approach (MPRNet) by 0.25 dB on average, but only accounts for 11.7% and 42.1% of its computational cost and parameters.
科研通智能强力驱动
Strongly Powered by AbleSci AI