Dynamic Distribution Calibration Method for Few-Shot Learning

Author:

Khan Majid Habib1,Liu Jinwei Zhao1,Hei Xinhong1,Liu Jiedong1,Zhang Hongtao1,Li Shuangjiang1,Liu Yu1,Imran Muhammad1

Affiliation:

1. Xi’an University of Technology

Abstract

Abstract

Convolutional neural network (CNN) is frequently used in image classification. However, obtaining sufficient labelled data for training is difficult because labelling data is costly. Learning from a limited number of samples creates challenges since the learned model may become overfitted due to the biased distribution caused by a few training samples and the pow learning algorithm. This paper proposed a dynamic distribution calibration method for the few shot-learning. First, the base and new class samples were normalized using the normalization technique to eliminate the effect of different feature magnitudes. A pre-trained feature extraction model extracts the sample feature vectors of the base class and the new class. The distribution characteristics of the adjacent and remote base classes are dynamically selected for a new class sample in an embedding space by a threshold value method. A similar class usually has a similar feature distribution, such as mean and variance. So, the means and variance of the Gaussian distribution can be transferred between similar classes. In the paper, the feature distribution is assumed to follow the Gaussian distribution. Then, the distributional features of each sample in the new class are calibrated using the corrected hyperparameter based on the distribution features of the adjacent base class and far base class in the embedding space. Finally, the calibrated distribution features augment the sample set of the new class. In some experiments on the benchmark datasets miniImagenet and CUB, the new dynamic distribution calibration method achieves up to 4% accuracy gains in some few-shot classification challenges and achieves superior performance.

Publisher

Research Square Platform LLC

Reference44 articles.

1. Generalizing from a few examples: A survey on few-shot learning;Wang Y;ACM Comput Surv (csur),2020

2. A union of deep learning and swarm-based optimization for 3D human action recognition;Basak H;Sci Rep,2022

3. Zhuang F et al (2020) A comprehensive survey on transfer learning. Proceedings of the IEEE, 109(1): pp. 43–76

4. Meta-seg: A survey of meta-learning for image segmentation;Luo S;Pattern Recogn,2022

5. Wang Y et al (2020) Instance credibility inference for few-shot learning. in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3