公制(单位)
人工智能
模式识别(心理学)
集成学习
计算机科学
特征(语言学)
光学(聚焦)
图像(数学)
上下文图像分类
透视图(图形)
相似性(几何)
机器学习
光学
经济
哲学
物理
语言学
运营管理
作者
Hang Wang,Duanbing Chen
出处
期刊:Journal of physics
[IOP Publishing]
日期:2022-01-01
卷期号:2171 (1): 012027-012027
被引量:3
标识
DOI:10.1088/1742-6596/2171/1/012027
摘要
Abstract In the case of few labelled image data samples, image classification is a difficult challenge, which is called few-shot image classification. Recently, many methods based on metric learning have been proposed. Most of these methods mainly focus on the representations of global image-level features or local feature-level descriptors. However, these methods calculate similarity from a single metric learning perspective. Motivated by ensemble learning, a novel Ensemble Metric Learning (EML) method for few-shot image classification is proposed, which not only utilizes label propagation, but also considers image-level and local feature-level descriptor metrics. The experimental results show that the proposed method can effectively improve the classification accuracy by ensemble learning.
科研通智能强力驱动
Strongly Powered by AbleSci AI