Deep Clustering With Hybrid-Grained Contrastive and Discriminative Learning
IEEE Transactions on Circuits and Systems for Video Technology · 2024-10 · 34 (10) · 9472-9483
DOI: 10.1109/tcsvt.2024.3399596 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2024-10. Verfasst von Dong Huang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Project, Guangdong Forestry Science Data Center.
Abstract (Originalsprache)
Deep contrastive clustering has recently gained significant attention due to its advantageous ability to leverage the contrastive learning paradigm for joint representation learning and clustering. However, previous deep contrastive clustering approaches mostly focus on instance discrimination or cluster discrimination, which often overlook the rich semantic information latent in the vast intermediate levels of granularity between instances and clusters. Moreover, they are typically prone to utilizing relationships only within the same level of granularity, e.g., instance-instance relationships and cluster-cluster relationships, but frequently neglect the interactions between different granularity-levels. To tackle these issues, this paper presents a novel end-to-end deep contrastive clustering approach termed Deep Clustering with Hybrid-Grained Contrastive and Discriminative Learning (DCHL). Particularly, the instance-level contrastive learning and cluster-level contrastive learning are first formulated, where the cluster-level contrastive learning is further split into fine-grained and coarse-grained branches. To capture global dependencies, the cluster-level contrastiveness is explored on the coarse-grained cluster branch. Meanwhile, to capture hybrid-grained relationships, the dual-level instance-group discrimination learning is enforced between the instance branch and the fine-grained cluster branch, where the self instance-group discrimination and the cross instance-group discrimination are simultaneously optimized for enhancing the deep clustering performance. Experiments on five challenging image datasets confirm the superiority of DCHL over the state-of-the-art. Code available: https://github.com/dengxiaozhi/DCHL.
Förderung
- National Natural Science Foundation of China
- Guangdong Project
- Guangdong Forestry Science Data Center
- Guangdong Provincial Key Laboratory of Intellectual Property and Big Data
Zitieren
APA
Huang, D., Deng, X., Chen, D., Wen, Z., Sun, W., Wang, C., & Lai, J. (2024). Deep Clustering With Hybrid-Grained Contrastive and Discriminative Learning. IEEE Transactions on Circuits and Systems for Video Technology, 34(10), 9472-9483. https://doi.org/10.1109/tcsvt.2024.3399596
Vancouver
Huang D, Deng X, Chen D, Wen Z, Sun W, Wang C, et al. Deep Clustering With Hybrid-Grained Contrastive and Discriminative Learning. IEEE Transactions on Circuits and Systems for Video Technology. 2024;34(10):9472-9483. doi:10.1109/tcsvt.2024.3399596
BibTeX
@article{Huang2024,
author = {Huang, Dong and Deng, Xiaozhi and Chen, Ding-Hua and Wen, Zihao and Sun, Weijun and Wang, Chang-Dong and Lai, Jian-Huang},
title = {Deep Clustering With Hybrid-Grained Contrastive and Discriminative Learning},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2024},
volume = {34},
number = {10},
pages = {9472--9483},
doi = {10.1109/tcsvt.2024.3399596}
}
EUVIMED