Label Distribution Learning
583
TL;DR: This paper proposes six working LDL algorithms in three ways: problem transformation, algorithm adaptation, and specialized algorithm design, and results show clear advantages of the specialized algorithms, which indicates the importance of special design for the characteristics of the LDL problem.
read more
Abstract: Although multi-label learning can deal with many problems with label ambiguity, it does not fit some real applications well where the overall distribution of the importance of the labels matters. This paper proposes a novel learning paradigm named label distribution learning (LDL) for such kind of applications. The label distribution covers a certain number of labels, representing the degree to which each label describes the instance. LDL is a more general learning framework which includes both single-label and multi-label learning as its special cases. This paper proposes six working LDL algorithms in three ways: problem transformation, algorithm adaptation, and specialized algorithm design. In order to compare the performance of the LDL algorithms, six representative and diverse evaluation measures are selected via a clustering analysis, and the first batch of label distribution datasets are collected and made publicly available. Experimental results on one artificial and 15 real-world datasets show clear advantages of the specialized algorithms, which indicates the importance of special design for the characteristics of the LDL problem.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Binary relevance for multi-label learning: an overview
TL;DR: This paper aims to review the state of the art of binary relevance from three perspectives, and some of the recent studies on binary relevance aimed at issues other than label correlation exploitation are introduced.
414
Deep Label Distribution Learning With Label Ambiguity
TL;DR: The proposed deep label distribution learning (DLDL) method effectively utilizes the label ambiguity in both feature learning and classifier learning, which help prevent the network from overfitting even when the training set is small.
Deep Label Distribution Learning with Label Ambiguity
TL;DR: Deep Label Distribution Learning (LDL) as mentioned in this paper learns the label distribution by minimizing a Kullback-Leibler divergence between the predicted and ground-truth label distributions using deep ConvNets.
358
Mean-Variance Loss for Deep Age Estimation from a Face
Hongyu Pan,Hu Han,Shiguang Shan,Xilin Chen +3 more
- 18 Jun 2018
TL;DR: A new loss function, called mean-variance loss, is proposed for robust age estimation via distribution learning, which penalizes difference between the mean and variance of the estimated age distribution and the ground-truth age.
Label Distribution Learning on Auxiliary Label Space Graphs for Facial Expression Recognition
Shikai Chen,Jianfeng Wang,Yuedong Chen,Zhongchao Shi,Xin Geng,Yong Rui +5 more
- 14 Jun 2020
TL;DR: This work proposes a novel approach named Label Distribution Learning on Auxiliary Label Space Graphs (LDL-ALSG) that leverages the topological information of the labels from related but more distinct tasks, such as action unit recognition and facial landmark detection.
References
Cluster analysis and display of genome-wide expression patterns
TL;DR: A system of cluster analysis for genome-wide expression data from DNA microarray hybridization is described that uses standard statistical algorithms to arrange genes according to similarity in pattern of gene expression, finding in the budding yeast Saccharomyces cerevisiae that clustering gene expression data groups together efficiently genes of known similar function.
Multitask Learning
Rich Caruana
- 01 Jul 1997
TL;DR: Multi-task Learning (MTL) as mentioned in this paper is an approach to inductive transfer that improves generalization by using the domain information contained in the training signals of related tasks as an inductive bias.
Face Description with Local Binary Patterns: Application to Face Recognition
TL;DR: This paper presents a novel and efficient facial image representation based on local binary pattern (LBP) texture features that is assessed in the face recognition problem under different challenges.
6.2K
Uncovering the overlapping community structure of complex networks in nature and society
TL;DR: After defining a set of new characteristic quantities for the statistics of communities, this work applies an efficient technique for exploring overlapping communities on a large scale and finds that overlaps are significant, and the distributions introduced reveal universal features of networks.
An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression
TL;DR: Kernel and nearest-neighbor regression estimators are local versions of univariate location estimators, and so they can readily be introduced to beginning students and consulting clients who are familiar with such summaries as the sample mean and median.
Related Papers (5)
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
Karl Ricanek,Tamirat Tesafaye +1 more
- 10 Apr 2006