Clustering by Maximizing Mutual Information Across Views
- URL: http://arxiv.org/abs/2107.11635v1
- Date: Sat, 24 Jul 2021 15:36:49 GMT
- Title: Clustering by Maximizing Mutual Information Across Views
- Authors: Kien Do, Truyen Tran, Svetha Venkatesh
- Abstract summary: We propose a novel framework for image clustering that incorporates joint representation learning and clustering.
Our method significantly outperforms state-of-the-art single-stage clustering methods across a variety of image datasets.
- Score: 62.21716612888669
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We propose a novel framework for image clustering that incorporates joint
representation learning and clustering. Our method consists of two heads that
share the same backbone network - a "representation learning" head and a
"clustering" head. The "representation learning" head captures fine-grained
patterns of objects at the instance level which serve as clues for the
"clustering" head to extract coarse-grain information that separates objects
into clusters. The whole model is trained in an end-to-end manner by minimizing
the weighted sum of two sample-oriented contrastive losses applied to the
outputs of the two heads. To ensure that the contrastive loss corresponding to
the "clustering" head is optimal, we introduce a novel critic function called
"log-of-dot-product". Extensive experimental results demonstrate that our
method significantly outperforms state-of-the-art single-stage clustering
methods across a variety of image datasets, improving over the best baseline by
about 5-7% in accuracy on CIFAR10/20, STL10, and ImageNet-Dogs. Further, the
"two-stage" variant of our method also achieves better results than baselines
on three challenging ImageNet subsets.
Related papers
- CLC: Cluster Assignment via Contrastive Representation Learning [9.631532215759256]
We propose Contrastive Learning-based Clustering (CLC), which uses contrastive learning to directly learn cluster assignment.
We achieve 53.4% accuracy on the full ImageNet dataset and outperform existing methods by large margins.
arXiv Detail & Related papers (2023-06-08T07:15:13Z) - Unified Multi-View Orthonormal Non-Negative Graph Based Clustering
Framework [74.25493157757943]
We formulate a novel clustering model, which exploits the non-negative feature property and incorporates the multi-view information into a unified joint learning framework.
We also explore, for the first time, the multi-model non-negative graph-based approach to clustering data based on deep features.
arXiv Detail & Related papers (2022-11-03T08:18:27Z) - Improving Image Clustering through Sample Ranking and Its Application to
remote--sensing images [14.531733039462058]
We propose a novel method by first ranking samples within each cluster based on the confidence in their belonging to the current cluster.
For ranking the samples, we developed a method for computing the likelihood of samples belonging to the current clusters based on whether they are situated in densely populated neighborhoods.
We show that our method can be effectively applied to remote-sensing images.
arXiv Detail & Related papers (2022-09-26T12:10:02Z) - ACTIVE:Augmentation-Free Graph Contrastive Learning for Partial
Multi-View Clustering [52.491074276133325]
We propose an augmentation-free graph contrastive learning framework to solve the problem of partial multi-view clustering.
The proposed approach elevates instance-level contrastive learning and missing data inference to the cluster-level, effectively mitigating the impact of individual missing data on clustering.
arXiv Detail & Related papers (2022-03-01T02:32:25Z) - Large-Scale Hyperspectral Image Clustering Using Contrastive Learning [18.473767002905433]
We present a scalable deep online clustering model, named Spectral-Spatial Contrastive Clustering (SSCC)
We exploit a symmetric twin neural network comprised of a projection head with a dimensionality of the cluster number to conduct dual contrastive learning from a spectral-spatial augmentation pool.
The resulting approach is trained in an end-to-end fashion by batch-wise optimization, making it robust in large-scale data and resulting in good generalization ability for unseen data.
arXiv Detail & Related papers (2021-11-15T17:50:06Z) - Deep Attention-guided Graph Clustering with Dual Self-supervision [49.040136530379094]
We propose a novel method, namely deep attention-guided graph clustering with dual self-supervision (DAGC)
We develop a dual self-supervision solution consisting of a soft self-supervision strategy with a triplet Kullback-Leibler divergence loss and a hard self-supervision strategy with a pseudo supervision loss.
Our method consistently outperforms state-of-the-art methods on six benchmark datasets.
arXiv Detail & Related papers (2021-11-10T06:53:03Z) - Learning Statistical Representation with Joint Deep Embedded Clustering [2.1267423178232407]
StatDEC is an unsupervised framework for joint statistical representation learning and clustering.
Our experiments show that using these representations, one can considerably improve results on imbalanced image clustering across a variety of image datasets.
arXiv Detail & Related papers (2021-09-11T09:26:52Z) - Graph Contrastive Clustering [131.67881457114316]
We propose a novel graph contrastive learning framework, which is then applied to the clustering task and we come up with the Graph Constrastive Clustering(GCC) method.
Specifically, on the one hand, the graph Laplacian based contrastive loss is proposed to learn more discriminative and clustering-friendly features.
On the other hand, a novel graph-based contrastive learning strategy is proposed to learn more compact clustering assignments.
arXiv Detail & Related papers (2021-04-03T15:32:49Z) - Learning to Cluster Faces via Confidence and Connectivity Estimation [136.5291151775236]
We propose a fully learnable clustering framework without requiring a large number of overlapped subgraphs.
Our method significantly improves clustering accuracy and thus performance of the recognition models trained on top, yet it is an order of magnitude more efficient than existing supervised methods.
arXiv Detail & Related papers (2020-04-01T13:39:37Z)
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.