Abstract

Clustering is a class of unsupervised learning methods that has been extensively applied and studied in computer vision. Little work has been done to adapt it to the end-to-end training of visual features on large-scale datasets. In this work, we present DeepCluster, a clustering method that jointly learns the parameters of a neural network and the cluster assignments of the resulting features. DeepCluster iteratively groups the features with a standard clustering algorithm, k-means, and uses the subsequent assignments as supervision to update the weights of the network. We apply DeepCluster to the unsupervised training of convolutional neural networks on large datasets like ImageNet and YFCC100M. The resulting model outperforms the current state of the art by a significant margin on all the standard benchmarks.

Keywords

Computer scienceCluster analysisMargin (machine learning)Artificial intelligenceUnsupervised learningPattern recognition (psychology)Convolutional neural networkArtificial neural networkMachine learningClass (philosophy)

Related Publications

Publication Info

Year
2018
Type
book-chapter
Pages
139-156
Citations
2355
Access
Closed

External Links

Download PDF (Free) View on DOI.org arXiv PubMed Semantic Scholar

Social Impact

Altmetric
PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

2355
OpenAlex
229
Influential

Cite This

Mathilde Caron, Piotr Bojanowski, Armand Joulin et al. (2018). Deep Clustering for Unsupervised Learning of Visual Features. Lecture notes in computer science , 139-156. https://doi.org/10.1007/978-3-030-01264-9_9

Identifiers

DOI
10.1007/978-3-030-01264-9_9
PMID
41357951
PMCID
PMC12678682
arXiv
1807.05520

Data Quality

Data completeness: 79%