Earticle

초록

영어

The goal of few-shot learning is to use limited labeled samples to achieve effective classification results. To mine the features of images in the limited number of samples, some researchers proposed to mine salient features to improve the classification effect. However, they ignore the use of secondary salient features. Therefore, we propose to use secondary salient features to supplement the deficiency of salient features. Combining with the foreground extraction network and the graph neural network, a better classification effect is obtained in the experiment.

목차

Abstract
I. INTRODUCTION
II. METHODOLOGY
A. Problem definition
B. Overall Framework
C. Loss
III. EXPERIMENTS
A. Datasets
B. Few-Shot Classification
IV. CONCLUSION
REFERENCES

저자

• Chuang Liu [ Department of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing, China ] Corresponding Author
• Hu Pan [ Department of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing, China ]

참고문헌