Incomplete label distribution learning based on supervised neighborhood information

2019 ◽  
Vol 11 (1) ◽  
pp. 111-121
Author(s):  
Xue-Qiang Zeng ◽  
Su-Fen Chen ◽  
Run Xiang ◽  
Guo-Zheng Li ◽  
Xue-Feng Fu
Keyword(s):  
Neighborhood Information ◽  
Label Distribution Learning ◽  
Label Distribution

Active label distribution learning

2021 ◽  
Vol 436 ◽  
pp. 12-21
Author(s):  
Xinyue Dong ◽  
Shilin Gu ◽  
Wenzhang Zhuge ◽  
Tingjin Luo ◽  
Chenping Hou
Keyword(s):  
Label Distribution Learning ◽  
Label Distribution

Label distribution learning by maintaining label ranking relation

2021 ◽  
pp. 1-1
Author(s):  
Xiuyi Jia ◽  
Xiaoxia Shen ◽  
Weiwei Li ◽  
Yunan Lu ◽  
Jihua Zhu
Keyword(s):  
Label Ranking ◽  
Label Distribution Learning ◽  
Label Distribution

Adaptive Variance Based Label Distribution Learning for Facial Age Estimation

2020 ◽  
pp. 379-395
Author(s):  
Xin Wen ◽  
Biying Li ◽  
Haiyun Guo ◽  
Zhiwei Liu ◽  
Guosheng Hu ◽  
...  
Keyword(s):  
Age Estimation ◽  
Label Distribution Learning ◽  
Label Distribution ◽  
Facial Age

scholarly journals Label Enhancement for Label Distribution Learning via Prior Knowledge

2020 ◽  
Author(s):  
Yongbiao Gao ◽  
Yu Zhang ◽  
Xin Geng
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Emotion Recognition ◽  
Prior Knowledge ◽  
Decision Process ◽  
Age Estimation ◽  
State Of The Art ◽  
Learning Agent ◽  
Label Distribution Learning ◽  
Label Distribution

Label distribution learning (LDL) is a novel machine learning paradigm that gives a description degree of each label to an instance. However, most of training datasets only contain simple logical labels rather than label distributions due to the difficulty of obtaining the label distributions directly. We propose to use the prior knowledge to recover the label distributions. The process of recovering the label distributions from the logical labels is called label enhancement. In this paper, we formulate the label enhancement as a dynamic decision process. Thus, the label distribution is adjusted by a series of actions conducted by a reinforcement learning agent according to sequential state representations. The target state is defined by the prior knowledge. Experimental results show that the proposed approach outperforms the state-of-the-art methods in both age estimation and image emotion recognition.

scholarly journals COS-LDL: Label Distribution Learning by Cosine-Based Distance-Mapping Correlation

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 63961-63970
Author(s):  
Heng-Ru Zhang ◽  
Yu-Ting Huang ◽  
Yuan-Yuan Xu ◽  
Fan Min
Keyword(s):  
Label Distribution Learning ◽  
Distance Mapping ◽  
Label Distribution
Sign in / Sign up

Export Citation Format

Share Document