.png){kind=icon}
返回
Frequency disentangled residual network
.png){kind=icon}
OA
AI
DOI：10.1007/s00530-023-01232-5.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Residual networks (ResNets) have been utilized for various computer vision and image processing applications. The residual connection improves the training of the network with better gradient flow. A residual block consists of a few convolutional layers having trainable parameters, which leads to overfitting. Moreover, the present residual networks are not able to utilize the high- and low-frequency information suitably, which also challenges the generalization capability of the network. In this paper, a frequency-disentangled residual network (FDResNet) is proposed to tackle these issues. Specifically, FDResNet includes separate connections in the residual block for low- and high-frequency components, respectively. Basically, the proposed model disentangles the low- and high-frequency components to increase the generalization ability. Moreover, the computation of low- and high-frequency components using fixed filters further avoids the overfitting. The proposed model is tested on benchmark CIFAR-10/100, Caltech, and TinyImageNet datasets for image classification. The performance of the proposed model is also tested in the image retrieval framework. It is noticed that the proposed model outperforms its counterpart residual model. The effect of kernel size and standard deviation is also evaluated. The impact of the frequency disentangling is also analyzed using a saliency map.
Keyword:
Deep learning
ResNet
Image classification
Frequency disentanglement
期刊
IF:
3.1
论文数:
2.8K
被引数:
2.7K
机构
引用论文
A lightweight CNN-based algorithm and implementation on embedded system for real-time face recognition基于轻量级CNN的实时人脸识别算法及嵌入式系统实现.png)
MULTIMEDIA SYSTEMS
MULTIMEDIA SYSTEMSIF3.1
PREAI
分享收藏
查看更多内容