2016
DOI: 10.1109/tkde.2016.2545658
|View full text |Cite
|
Sign up to set email alerts
|

Label Distribution Learning

Abstract: 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… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
408
0
2

Year Published

2017
2017
2024
2024

Publication Types

Select...
5
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 539 publications
(410 citation statements)
references
References 31 publications
0
408
0
2
Order By: Relevance
“…Several work incorporate the model weights learned from a large-scale general dataset [Deng et al, 2009] and finetune the state-of-the-art CNNs for the task of visual emotion prediction [Campos et al, 2015]. [You et al, 2015;2016] propose a novel progressive CNN architecture, namely PCNN, to make use of large noisy web data, and further perform benchmarking analysis on the Flickr and Instagram (FI) dataset, which is currently the largest single label dataset containing 23,308 affective images. In [Rao et al, 2016], a multi-level deep network (MldeNet) is proposed to unify both low-level and high-level information of images.…”
Section: Image Emotion Classificationmentioning
confidence: 99%
See 2 more Smart Citations
“…Several work incorporate the model weights learned from a large-scale general dataset [Deng et al, 2009] and finetune the state-of-the-art CNNs for the task of visual emotion prediction [Campos et al, 2015]. [You et al, 2015;2016] propose a novel progressive CNN architecture, namely PCNN, to make use of large noisy web data, and further perform benchmarking analysis on the Flickr and Instagram (FI) dataset, which is currently the largest single label dataset containing 23,308 affective images. In [Rao et al, 2016], a multi-level deep network (MldeNet) is proposed to unify both low-level and high-level information of images.…”
Section: Image Emotion Classificationmentioning
confidence: 99%
“…However, both of the optimization objective functions fail to utilize sentiment ambiguity and similarity information among image categories. [Geng, 2016] proposes a novel machine learning paradigm for describing the exact role of each label, which contains three strategies for the algorithms, i.e. problem transfer (PT), algorithm adaption (AA), and specialized algorithms (SA).…”
Section: Image Emotion Classificationmentioning
confidence: 99%
See 1 more Smart Citation
“…In label distribution learning (LDL) problems [47], otherwise known as probabilistic class label problems [75], any instance can be described in different degrees by each label. This can be modeled as a discrete distribution over the labels, where the probability of a label given a specific instance is called its degree of description.…”
Section: Label Distribution Learningmentioning
confidence: 99%
“…-LDL. A LDL problem can be reduced to multiclass classification by extracting as many single-label examples as labels for each one of the training instances [47]. These new examples are assigned a class corresponding to each label and weighted according to its degree of description.…”
Section: Problem Transformationmentioning
confidence: 99%