contrastive clustering | [2009.09687] Contrastive Clustering

Keyword	CPC	PCC	Volume	Score	Length of keyword
contrastive clustering	1.3	0.7	1746	39	22
contrastive	1.61	0.4	5221	55	11
clustering	0.15	0.5	1509	36	10

Keyword	CPC	PCC	Volume	Score
contrastive clustering	0.3	1	551	71
contrastive clustering github	0.66	0.8	1672	65
contrastive clustering aaai	0.28	1	8124	74
contrastive clustering aaai 2021	1.69	0.3	8746	81
graph contrastive clustering	1.37	0.7	2409	56
simple contrastive graph clustering	0.21	0.3	2356	14
multi-view contrastive graph clustering	1.78	0.3	3299	16
vision transformer for contrastive clustering	1.34	0.5	8053	100
contrastive learning clustering	0.25	0.2	5489	23
deep temporal contrastive clustering	0.05	0.5	2748	66
strongly augmented contrastive clustering	0.01	0.4	1138	89

Search Results related to contrastive clustering on Search Engine

[2009.09687] Contrastive Clustering - arXiv.org
arxiv.org:443

https://arxiv.org:443/abs/2009.09687

WEBSep 21, 2020 · Yunfan Li, Peng Hu, Zitao Liu, Dezhong Peng, Joey Tianyi Zhou, Xi Peng. In this paper, we propose a one-stage online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- …

DA: 46 PA: 68 MOZ Rank: 47

Contrastive Clustering | Proceedings of the AAAI Conference on
aaai.org:443

https://ojs.aaai.org:443/index.php/AAAI/article/view/17037

WEBMay 18, 2021 · Extensive experimental results show that CC remarkably outperforms 17 competitive clustering methods on six challenging image benchmarks. In particular, CC achieves an NMI of 0.705 (0.431) on the CIFAR-10 (CIFAR-100) dataset, which is an up to 19% (39%) performance improvement compared with the best baseline.

DA: 80 PA: 5 MOZ Rank: 92

1 Contrastive Clustering - arXiv.org
arxiv.org:443

https://arxiv.org:443/pdf/2009.09687.pdf

WEBExtensive experimental results show that CC remarkably outperforms 17 competitive clustering methods on six challenging image benchmarks. In particular, CC achieves an NMI of 0.705 (0.431) on the CIFAR-10 (CIFAR-100) dataset, which is an up to 19% (39%) performance improvement compared with the best baseline.

DA: 97 PA: 70 MOZ Rank: 18

Safe Contrastive Clustering - Springer
springer.com:443

https://link.springer.com:443/content/pdf/10.1007/978-3-031-27077-2_23.pdf?pdf=inline%20link

WEBAbstract. Contrastive clustering is an effective deep clustering app-roach, which learns both instance-level consistency and cluster-level con-sistency in a contrastive learning fashion.

DA: 22 PA: 67 MOZ Rank: 91

Safe Contrastive Clustering | SpringerLink
springer.com:443

https://link.springer.com:443/chapter/10.1007/978-3-031-27077-2_23

WEBMar 29, 2023 · Contrastive clustering is an effective deep clustering approach, which learns both instance-level consistency and cluster-level consistency in a contrastive learning fashion. However, the strategies of data augmentation used …

DA: 50 PA: 82 MOZ Rank: 51

Strongly augmented contrastive clustering - ScienceDirect
sciencedirect.com:443

https://www.sciencedirect.com:443/science/article/pii/S003132032300170X

WEBJul 1, 2023 · Strongly augmented contrastive clustering. Xiaozhi Deng a. , Dong Huang a b. , Ding-Hua Chen a. , Chang-Dong Wang c d. , Jian-Huang Lai c d. Show more. Add to Mendeley. https://doi.org/10.1016/j.patcog.2023.109470 Get rights and content. Highlights. •. This paper jointly exploits strong and weak augmentations for …

DA: 40 PA: 17 MOZ Rank: 52

Graph Contrastive Clustering - CVF Open Access
thecvf.com:443

https://openaccess.thecvf.com:443/content/ICCV2021/papers/Zhong_Graph_Contrastive_Clustering_ICCV_2021_paper.pdf

WEBFor clustering learning, a novel graph-based contrastive learning strategy is proposed to learn more compact clustering assignments. Both of them can help to decrease the intra-class variance and increase inter-class variance. Experimental results on six challenging datasets validate the effectiveness of the proposed method.

DA: 31 PA: 19 MOZ Rank: 86

Deep Clustering by Graph Attention Contrastive Learning - MDPI
mdpi.com:443

https://www.mdpi.com:443/2079-9292/12/11/2489

WEBMay 31, 2023 · Contrastive learning shows great potential in deep clustering. It uses constructed pairs to discover the feature distribution that is required for the clustering task.

DA: 23 PA: 33 MOZ Rank: 27

Multi-view Contrastive Graph Clustering - NeurIPS
neurips.cc:443

https://proceedings.neurips.cc:443/paper/2021/file/10c66082c124f8afe3df4886f5e516e0-Paper.pdf

WEBSpecifcally, inspired by the success of contrastive learning, we propose multi-view contrastive graph clustering (MCGC) method to learn a consensus graph since the original graph could be noisy or incomplete and is not directly applicable.

DA: 18 PA: 55 MOZ Rank: 49

Contrastive Clustering - AAAI
aaai.org:443

https://aaai.org:443/papers/08547-contrastive-clustering/

WEBIn this paper, we propose an online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning. To be specific, for a given dataset, the positive and negative instance pairs are constructed through data augmentations and then projected into a feature space.

DA: 85 PA: 17 MOZ Rank: 78