Contrastive Label Enhancement

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.

[1]  Shengsheng Qian,et al.  Integrating Multi-Label Contrastive Learning With Dual Adversarial Graph Neural Networks for Cross-Modal Retrieval , 2022, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Jun Shu,et al.  Variational Label Enhancement , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Jihua Zhu,et al.  Generalized Label Enhancement With Sample Correlations , 2020, IEEE Transactions on Knowledge and Data Engineering.

[4]  K. Wang,et al.  Sequential Label Enhancement. , 2022, IEEE Transactions on Neural Networks and Learning Systems.

[5]  Clayton D. Scott,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence , 2022, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Xin Geng,et al.  Fusion Label Enhancement for Multi-Label Learning , 2022, IJCAI.

[7]  Chetan Ramaiah,et al.  Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Yinghuan Shi,et al.  Label Distribution Learning for Generalizable Multisource Person Re-Identification , 2022, IEEE Transactions on Information Forensics and Security.

[9]  Carla P. Gomes,et al.  Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification , 2021, ICML.

[10]  Xinyu Dai,et al.  Contrastive Learning-Enhanced Nearest Neighbor Mechanism for Multi-Label Text Classification , 2022, ACL.

[11]  Junnan Li,et al.  Prototypical Contrastive Learning of Unsupervised Representations , 2020, ICLR.

[12]  Ning Xu,et al.  Label Enhancement for Label Distribution Learning , 2018, IEEE Transactions on Knowledge and Data Engineering.

[13]  Yu Zhang,et al.  Label Enhancement for Label Distribution Learning via Prior Knowledge , 2020, IJCAI.

[14]  Pierre H. Richemond,et al.  Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning , 2020, NeurIPS.

[15]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[16]  Krzysztof J. Cios,et al.  An evolutionary approach to build ensembles of multi-label classifiers , 2019, Inf. Fusion.

[17]  Chun Yang,et al.  Multi-label Ranking with LSTM ^2 for Document Classification , 2016, CCPR.

[18]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[19]  Xin Geng,et al.  Label Distribution Learning , 2013, 2013 IEEE 13th International Conference on Data Mining Workshops.

[20]  Xin Geng,et al.  Leveraging Implicit Relative Labeling-Importance Information for Effective Multi-label Learning , 2015, 2015 IEEE International Conference on Data Mining.

[21]  Xin Geng,et al.  Crowd counting in public video surveillance by label distribution learning , 2015, Neurocomputing.

[22]  Sebastián Ventura,et al.  Multi‐label learning: a review of the state of the art and ongoing research , 2014, WIREs Data Mining Knowl. Discov..

[23]  Odile Papini,et al.  Information Fusion , 2014, Computer Vision, A Reference Guide.

[24]  Philip S. Yu,et al.  2014 IEEE International Conference on Data Mining , 2014 .

[25]  Zhi-Hua Zhou,et al.  Facial Age Estimation by Learning from Label Distributions , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[27]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[28]  Günther Palm,et al.  A Study of the Robustness of KNN Classifiers Trained Using Soft Labels , 2006, ANNPR.

[29]  Jun Wang,et al.  A 3D facial expression database for facial behavior research , 2006, 7th International Conference on Automatic Face and Gesture Recognition (FGR06).

[30]  Zhang Yi,et al.  Fuzzy SVM with a new fuzzy membership function , 2006, Neural Computing & Applications.

[31]  D. Botstein,et al.  Cluster analysis and display of genome-wide expression patterns. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[32]  Michael J. Lyons,et al.  Coding facial expressions with Gabor wavelets , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[33]  Benjamin W. Wah,et al.  Editorial: Two Named to Editorial Board of IEEE Transactions on Knowledge and Data Engineering , 1996 .

[34]  R. Hecht-Nielsen,et al.  Neurocomputing , 1990, NATO ASI Series.

[35]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[36]  O. Bagasra,et al.  Proceedings of the National Academy of Sciences , 1914, Science.