Contrastive Label Enhancement
- URL: http://arxiv.org/abs/2305.09500v1
- Date: Tue, 16 May 2023 14:53:07 GMT
- Title: Contrastive Label Enhancement
- Authors: Yifei Wang, Yiyang Zhou, Jihua Zhu, Xinyuan Liu, Wenbiao Yan and
Zhiqiang Tian
- Abstract summary: We propose Contrastive Label Enhancement (ConLE) to generate high-level features by contrastive learning strategy.
We leverage the obtained high-level features to gain label distributions through a welldesigned training strategy.
- Score: 13.628665406039609
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Label distribution learning (LDL) is a new machine learning paradigm for
solving label ambiguity. Since it is difficult to directly obtain label
distributions, many studies are focusing on how to recover label distributions
from logical labels, dubbed label enhancement (LE). Existing LE methods
estimate label distributions by simply building a mapping relationship between
features and label distributions under the supervision of logical labels. They
typically overlook the fact that both features and logical labels are
descriptions of the instance from different views. Therefore, we propose a
novel method called Contrastive Label Enhancement (ConLE) which integrates
features and logical labels into the unified projection space to generate
high-level features by contrastive learning strategy. In this approach,
features and logical labels belonging to the same sample are pulled closer,
while those of different samples are projected farther away from each other in
the projection space. Subsequently, we leverage the obtained high-level
features to gain label distributions through a welldesigned training strategy
that considers the consistency of label attributes. Extensive experiments on
LDL benchmark datasets demonstrate the effectiveness and superiority of our
method.
Related papers
- Inaccurate Label Distribution Learning with Dependency Noise [52.08553913094809]
We introduce the Dependent Noise-based Inaccurate Label Distribution Learning (DN-ILDL) framework to tackle the challenges posed by noise in label distribution learning.
We show that DN-ILDL effectively addresses the ILDL problem and outperforms existing LDL methods.
arXiv Detail & Related papers (2024-05-26T07:58:07Z) - Scalable Label Distribution Learning for Multi-Label Classification [47.55261224881677]
Multi-label classification (MLC) refers to the problem of tagging a given instance with a set of relevant labels.
Most existing MLC methods design learning processes associated with the number of labels, which makes their computational complexity a bottleneck when scaling up to large-scale output space.
We propose a novel MLC learning method named Scalable Label Distribution Learning (SLDL) for multi-label classification which can describe different labels as distributions in a latent space.
arXiv Detail & Related papers (2023-11-28T06:52:53Z) - Label Distribution Learning from Logical Label [19.632157794117553]
Label distribution learning (LDL) is an effective method to predict the label description degree (a.k.a. label distribution) of a sample.
But annotating label distribution for training samples is extremely costly.
We propose a novel method to learn an LDL model directly from the logical label, which unifies LE and LDL into a joint model.
arXiv Detail & Related papers (2023-03-13T04:31:35Z) - Dist-PU: Positive-Unlabeled Learning from a Label Distribution
Perspective [89.5370481649529]
We propose a label distribution perspective for PU learning in this paper.
Motivated by this, we propose to pursue the label distribution consistency between predicted and ground-truth label distributions.
Experiments on three benchmark datasets validate the effectiveness of the proposed method.
arXiv Detail & Related papers (2022-12-06T07:38:29Z) - Label distribution learning via label correlation grid [9.340734188957727]
We propose a textbfLabel textbfCorrelation textbfGrid (LCG) to model the uncertainty of label relationships.
Our network learns the LCG to accurately estimate the label distribution for each instance.
arXiv Detail & Related papers (2022-10-15T03:58:15Z) - Acknowledging the Unknown for Multi-label Learning with Single Positive
Labels [65.5889334964149]
Traditionally, all unannotated labels are assumed as negative labels in single positive multi-label learning (SPML)
We propose entropy-maximization (EM) loss to maximize the entropy of predicted probabilities for all unannotated labels.
Considering the positive-negative label imbalance of unannotated labels, we propose asymmetric pseudo-labeling (APL) with asymmetric-tolerance strategies and a self-paced procedure to provide more precise supervision.
arXiv Detail & Related papers (2022-03-30T11:43:59Z) - A Label Dependence-aware Sequence Generation Model for Multi-level
Implicit Discourse Relation Recognition [31.179555215952306]
Implicit discourse relation recognition is a challenging but crucial task in discourse analysis.
We propose a Label Dependence-aware Sequence Generation Model (LDSGM) for it.
We develop a mutual learning enhanced training method to exploit the label dependence in a bottomup direction.
arXiv Detail & Related papers (2021-12-22T09:14:03Z) - Instance-Dependent Partial Label Learning [69.49681837908511]
Partial label learning is a typical weakly supervised learning problem.
Most existing approaches assume that the incorrect labels in each training example are randomly picked as the candidate labels.
In this paper, we consider instance-dependent and assume that each example is associated with a latent label distribution constituted by the real number of each label.
arXiv Detail & Related papers (2021-10-25T12:50:26Z) - A Study on the Autoregressive and non-Autoregressive Multi-label
Learning [77.11075863067131]
We propose a self-attention based variational encoder-model to extract the label-label and label-feature dependencies jointly.
Our model can therefore be used to predict all labels in parallel while still including both label-label and label-feature dependencies.
arXiv Detail & Related papers (2020-12-03T05:41:44Z) - Generalized Label Enhancement with Sample Correlations [24.582764493585362]
We propose two novel label enhancement methods, i.e., Label Enhancement with Sample Correlations (LESC) and generalized Label Enhancement with Sample Correlations (gLESC)
Benefitting from the sample correlations, the proposed methods can boost the performance of label enhancement.
arXiv Detail & Related papers (2020-04-07T03:32:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.