Fast and Dense Denoising Convolutional Neural Network
- Resource Type
- Conference
- Authors
- Zeng, Yuqiao; Liang, Tengfei; Jin, Yi; Li, Yidong; Wang, Zhigang
- Source
- 2021 International Conference on Digital Society and Intelligent Systems (DSInS) Digital Society and Intelligent Systems (DSInS), 2021 International Conference on. :250-254 Dec, 2021
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
Signal Processing and Analysis
Deep learning
Training
Computational modeling
Noise reduction
Neural networks
Urban areas
Lightweight structures
image denoising
convolutional neural networks
lightweighting of models
- Language
Deep neural networks show us their superior image denoising capability due to the powerful fitting ability. However, they suffer from the following drawbacks: (i) too deep neural networks often imply a very large number of parameters and considerable computational overhead; (ii) neural networks that are too deep are difficult to converge by training and may lead to degradation. In this study, we propose a novel denoising network called the fast and dense denoising convolutional neural network(FDDCNN). In particular, the depthwise separable convolutions in the fast module and the homogeneous cascade structure in the dense module can efficiently solve the above problem. Extensive experiments with publicly available datasets have shown that this model can have the same excellent denoising power as existing methods with fewer parameters and less computational overhead.