.png){kind=icon}
返回
Image classification based on self-distillation
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-022-04008-y.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Convolutional neural networks have been widely used in various application scenarios. To extend the application to some areas where accuracy is critical, researchers have been investigating methods to improve accuracy using deeper or broader network structures, which creates exponential growth in computation and storage costs and delays in response time. In this paper, we propose a self-distillation image classification algorithm that significantly improves performance while decreasing training costs. In traditional self-distillation, the student model needs to improve its ability to acquire global information and focus on key features due to the lack of guidance from the teacher model. For this reason, we improved the traditional self-distillation algorithm by using a positional attention module and a residual block with attention. Experimental results show that the method achieves better performance compared with traditional knowledge distillation methods and attention networks.
Keyword:
Image classification
Self-distillation
Attention
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
Caw’s Walking State Recognition Based on Accelerometers and Gyroscopes Installed on Ear-Tags and Collar-Tags基于安装在耳标和项圈上的加速度计和陀螺仪的Caw步行状态识别
PREAI
分享收藏Multi-attention embedded network for salient object detection面向显著目标检测的多关注嵌入式网络.png)
SOFT COMPUTING
SOFT COMPUTINGIF2.5
PREAI
分享收藏
Scale fusion light CNN for hyperspectral face recognition with knowledge distillation and attention mechanismAPPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏
查看更多内容