TFDMNet: A Novel Network Structure Combines the Time Domain and Frequency Domain Features
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916109969522688 |
|---|---|
| author | Pan, Hengyue Chen, Yixin Tian, Zhiliang Qiao, Peng Qiao, Linbo Li, Dongsheng |
| author_facet | Pan, Hengyue Chen, Yixin Tian, Zhiliang Qiao, Peng Qiao, Linbo Li, Dongsheng |
| contents | Convolutional neural network (CNN) has achieved impressive success in computer vision during the past few decades. The image convolution operation helps CNNs to get good performance on image-related tasks. However, it also has high computation complexity and hard to be parallelized. This paper proposes a novel Element-wise Multiplication Layer (EML) to replace convolution layers, which can be trained in the frequency domain. Theoretical analyses show that EMLs lower the computation complexity and easier to be parallelized. Moreover, we introduce a Weight Fixation mechanism to alleviate the problem of over-fitting, and analyze the working behavior of Batch Normalization and Dropout in the frequency domain. To get the balance between the computation complexity and memory usage, we propose a new network structure, namely Time-Frequency Domain Mixture Network (TFDMNet), which combines the advantages of both convolution layers and EMLs. Experimental results imply that TFDMNet achieves good performance on MNIST, CIFAR-10 and ImageNet databases with less number of operations comparing with corresponding CNNs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_15949 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TFDMNet: A Novel Network Structure Combines the Time Domain and Frequency Domain Features Pan, Hengyue Chen, Yixin Tian, Zhiliang Qiao, Peng Qiao, Linbo Li, Dongsheng Computer Vision and Pattern Recognition Machine Learning Convolutional neural network (CNN) has achieved impressive success in computer vision during the past few decades. The image convolution operation helps CNNs to get good performance on image-related tasks. However, it also has high computation complexity and hard to be parallelized. This paper proposes a novel Element-wise Multiplication Layer (EML) to replace convolution layers, which can be trained in the frequency domain. Theoretical analyses show that EMLs lower the computation complexity and easier to be parallelized. Moreover, we introduce a Weight Fixation mechanism to alleviate the problem of over-fitting, and analyze the working behavior of Batch Normalization and Dropout in the frequency domain. To get the balance between the computation complexity and memory usage, we propose a new network structure, namely Time-Frequency Domain Mixture Network (TFDMNet), which combines the advantages of both convolution layers and EMLs. Experimental results imply that TFDMNet achieves good performance on MNIST, CIFAR-10 and ImageNet databases with less number of operations comparing with corresponding CNNs. |
| title | TFDMNet: A Novel Network Structure Combines the Time Domain and Frequency Domain Features |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2401.15949 |