L2-norm prototypical networks for tackling the data shift problem in scene classification

Author:

Wei Tianyu1ORCID,Wang Jue2ORCID,Chen He1,Chen Liang13,Liu Wenchao4ORCID

Affiliation:

1. Beijing Key Laboratory of Embedded Real-time Information Processing Technology, Beijing Institute of Technology, Beijing, China

2. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China

3. Beijing Institute of Technology Chongqing Innovation Center, Beijing Institute of Technology, Chongqing, China

4. Department of Computer Science and Technology, Tsinghua University, Beijing, China

Funder

Chang Jiang Scholars

Hundred Leading Talent Project of Beijing Science and Technology

Publisher

Informa UK Limited

Subject

General Earth and Planetary Sciences

Reference51 articles.

1. Deep Open-Set Domain Adaptation for Cross-Scene Classification based on Adversarial Learning and Pareto Ranking

2. A Novel Statistical Method for Scene Classification Based on Multi-Object Categorization and Logistic Regression

3. Chen, W.Y., Y.C. Liu, Z. Kira, F. W. Yu-Chiang, and H. Jia-Bin. 2019. “A Closer Look at Few-shot Classification.” arXiv preprint arXiv:1904.04232.

4. Chen, Y., X. Wang, Z. Liu, X. Huijuan, and T. Darrell. 2020. “A New Meta-Baseline for Few-Shot Learning.” arXiv: Computer Vision and Pattern Recognition.

5. When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Intention-guided deep semi-supervised document clustering via metric learning;Journal of King Saud University - Computer and Information Sciences;2023-01

2. Impact of Regressand Stratification in Dataset Shift Caused by Cross-Validation;Mathematics;2022-07-21

3. Cosine Margin Prototypical Networks for Remote Sensing Scene Classification;IEEE Geoscience and Remote Sensing Letters;2022

4. RDPN: Tackling the Data Shift Problem in Remote Sensing Scene Classification;IEEE Geoscience and Remote Sensing Letters;2022

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