paper-with-me

홈 › Papers

Contrastive Hierarchical Clustering

2023-03-03 · Michał Znaleźniak, Przemysław Rola, Patryk Kaszuba, Jacek Tabor, Marek Śmieja

Deep clustering has been dominated by flat models, which split a dataset into a predefined number of groups. Although recent methods achieve an extremely high similarity with the ground truth on popular benchmarks, the information contained in the flat partition is limited. In this paper, we introduce CoHiClust, a Contrastive Hierarchical Clustering model based on deep neural networks, which can be applied to typical image data. By employing a self-supervised learning approach, CoHiClust distills the base network into a binary tree without access to any labeled data. The hierarchical clustering structure can be used to analyze the relationship between clusters, as well as to measure the similarity between data points. Experiments demonstrate that CoHiClust generates a reasonable structure of clusters, which is consistent with our intuition and image semantics. Moreover, it obtains superior clustering accuracy on most of the image datasets compared to the state-of-the-art flat clustering models.

📄 PDF Abstract BibTeX arXiv:2303.03389

Code (1)

michalznalezniak/contrastive-hierarchical-clustering 공식 구현 pytorch

Tasks

ClusteringDeep ClusteringImage ClusteringSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Average Pooling 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Residual Connection 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…

Similar Papers 제목 키워드 기반

Contrastive Multi-view Hyperbolic Hierarchical Clustering

2022-05-05 · Fangfei Lin, Bing Bai, Kun Bai, Yazhou Ren 외

Hierarchical clustering recursively partitions data at an increasingly finer granularity. In real-world applications, multi-view data have become increasingly important. This raises a less investigated problem, i.e., mul…

Clustering

MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series

2022-12-02 · Qianwen Meng, Hangwei Qian, Yong liu, Lizhen Cui 외

Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting. Contrastive learning has recently shown its promising representation lea…

ClusteringContrastive LearningRepresentation LearningTime Series+1

HCL: Improving Graph Representation with Hierarchical Contrastive Learning

2022-10-21 · Jun Wang, Weixun Li, Changyu Hou, Xin Tang 외

Contrastive learning has emerged as a powerful tool for graph representation learning. However, most contrastive learning methods learn features of graphs with fixed coarse-grained scale, which might underestimate either…

Contrastive LearningGraph ClassificationGraph Representation LearningNode Classification+2

Improved Face Representation via Joint Label Classification and Supervised Contrastive Clustering

2023-12-07 · Zhenduo Zhang

Face clustering tasks can learn hierarchical semantic information from large-scale data, which has the potential to help facilitate face recognition. However, there are few works on this problem. This paper explores it b…

ClusteringFace ClusteringFace Recognition

HGCL: Hierarchical Graph Contrastive Learning for User-Item Recommendation

2025-05-25 · Jiawei Xue, Zhen Yang, Haitao Lin, Ziji Zhang 외

Graph Contrastive Learning (GCL), which fuses graph neural networks with contrastive learning, has evolved as a pivotal tool in user-item recommendations. While promising, existing GCL methods often lack explicit modelin…

Contrastive Learning