arrow
Return

Continuous label distribution learning

delete2023-01-01
delete10
PRE
AI
X
Xingyu Zhao
Y
Yuexuan An
N
Ning Xu
X
Xin Geng *
DOI:10.1016/j.patcog.2022.109056delete
deleteOriginal
deleteShare
deleteSave
Abstract

Abstract

En 中文
Label distribution learning (LDL) is a suitable paradigm to deal with label ambiguity through learning the correlations among different labels. Most existing label distribution learning methods consider the labels to be discrete and directly establish the mapping from features to labels. However, in many real-world applications, labels naturally form a continuous distribution, which is ignored by the existing methods. As a result, the distribution information of labels can not be accurately described and finally affects the whole learning system. The goal of this paper is to propose a novel approach which can capture the continuous distribution of different labels explicitly and effectively. Specifically, we propose Continuous Label Distribution Learning (CLDL) which describes labels as a continuous density function and learns the distribution information of the labels in the latent space. In this way, the high-order correlations among different labels can be effectively extracted and only a few parameters for describing the continuous distribution need to be learned. Extensive description degree prediction experiments on real-world datasets validate the superiority of CLDL over the existing approaches.
Keywords:
Label distribution learning
Continuous label distribution
Label ambiguity
Label encoding
Label correlations

Journal

Pattern Recognition cover
Pattern Recognition
IF:
7.6
Papers:
1.4W
Citations:
6.1W

Organization

S
southeast university - china
Scholars:
0
Papers: 831
Citations: 4.1W
Cited Papers

Cited Papers

Beyond Ebola
err2016-02-19
err0
errOAAI
errJanet Currie; Bryan Grenfell; Jeremy Farrar
errShare
errSave
Learning multi-label scene classification
err2004-09-01
err2.0K
PREAI
errBoutell, MR; Luo, JB; Shen, XP; Brown, CM
errShare
errSave
errShare
errSave
errShare
errSave
errShare
errSave
ImageNet Large Scale Visual Recognition Challenge
err2015-04-11
err2.7W
PREAI
errRussakovsky, Olga; Deng, Jia; Su, Hao; Krause, Jonathan; Satheesh, Sanjeev; Ma, Sean; Huang, Zhiheng; Karpathy, Andrej; Khosla, Aditya; Bernstein, Michael; Berg, Alexander C.; Fei-Fei, Li
errShare
errSave
The American College of Rheumatology criteria for the classification and reporting of osteoarthritis of the hand
err2005-12-09
err0
PREAI
errR. Altman; G. Alarcon; D. Appelrouth; D. Bloch; D. Borenstein; K. Brandt; C. Brown; T. D. Cooke; W. Daniel; R. Gray; R. Greenwald; M. Hochberg; D. Howell; R. Ike; P. Kapila; D. Kaplan; W. Koopman; S. Longley; D. J. Mcshane; T. Medsger; B. Michel; W. Murphy; T. Osial; R. Ramsey‐Goldman; B. Rothschild; K. Stark; F. Wolfe
errShare
errSave
Label Distribution Learning with Label Correlations on Local Samples
err2021-04-01
err60
PREAI
errJia, Xiuyi; Li, Zechao; Zheng, Xiang; Li, Weiwei; Huang, Sheng-Jun
errShare
errSave
Charge-Transfer and Energy-Transfer Processes in π-Conjugated Oligomers and Polymers: A Molecular Picture
err2004-01-01
err0
PREAI
errJean‐Luc Brédas; David Beljonne; Veaceslav Coropceanu; Jérôme Cornil
errShare
errSave
researcher View more