The Group Loss++: A Deeper Look Into Group Loss for Deep Metric Learning
Author:
Affiliation:
1. Dynamic Vision and Learning Group, Technical University of Munich, München, Germany
2. Ca’ Foscari University of Venice, Venezia, VE, Italy
Funder
Alexander von Humboldt-Stiftung
Humboldt Research Fellowship
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
Applied Mathematics,Artificial Intelligence,Computational Theory and Mathematics,Computer Vision and Pattern Recognition,Software
Link
http://xplorestaging.ieee.org/ielx7/34/10008914/09745769.pdf?arnumber=9745769
Reference113 articles.
1. On the Foundations of Relaxation Labeling Processes
2. Multiplicative weights updates as a distributed constrained optimization algorithm: Convergence to second-order stationary points almost always;panageas;Proc Int Conf Mach Learn,2019
3. Going deeper with convolutions
4. An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology
5. Scene Labeling by Relaxation Operations
Cited by 5 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. Visual Embedding Augmentation in Fourier Domain for Deep Metric Learning;IEEE Transactions on Circuits and Systems for Video Technology;2023-10
2. Multi-proxy based deep metric learning;Information Sciences;2023-09
3. Ensemble of loss functions to improve generalizability of deep metric learning methods;Multimedia Tools and Applications;2023-07-24
4. Deep Metric Learning with Adaptively Composite Dynamic Constraints;IEEE Transactions on Pattern Analysis and Machine Intelligence;2023
5. Improved deep metric learning with local neighborhood component analysis;Information Sciences;2022-12
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