Cluster Contrast for Unsupervised Visual Representation Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Giakoumoglou, Nikolaos, Stathaki, Tania
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911060671332352
author Giakoumoglou, Nikolaos
Stathaki, Tania
author_facet Giakoumoglou, Nikolaos
Stathaki, Tania
contents We introduce Cluster Contrast (CueCo), a novel approach to unsupervised visual representation learning that effectively combines the strengths of contrastive learning and clustering methods. Inspired by recent advancements, CueCo is designed to simultaneously scatter and align feature representations within the feature space. This method utilizes two neural networks, a query and a key, where the key network is updated through a slow-moving average of the query outputs. CueCo employs a contrastive loss to push dissimilar features apart, enhancing inter-class separation, and a clustering objective to pull together features of the same cluster, promoting intra-class compactness. Our method achieves 91.40% top-1 classification accuracy on CIFAR-10, 68.56% on CIFAR-100, and 78.65% on ImageNet-100 using linear evaluation with a ResNet-18 backbone. By integrating contrastive learning with clustering, CueCo sets a new direction for advancing unsupervised visual representation learning.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12359
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cluster Contrast for Unsupervised Visual Representation Learning
Giakoumoglou, Nikolaos
Stathaki, Tania
Computer Vision and Pattern Recognition
Artificial Intelligence
We introduce Cluster Contrast (CueCo), a novel approach to unsupervised visual representation learning that effectively combines the strengths of contrastive learning and clustering methods. Inspired by recent advancements, CueCo is designed to simultaneously scatter and align feature representations within the feature space. This method utilizes two neural networks, a query and a key, where the key network is updated through a slow-moving average of the query outputs. CueCo employs a contrastive loss to push dissimilar features apart, enhancing inter-class separation, and a clustering objective to pull together features of the same cluster, promoting intra-class compactness. Our method achieves 91.40% top-1 classification accuracy on CIFAR-10, 68.56% on CIFAR-100, and 78.65% on ImageNet-100 using linear evaluation with a ResNet-18 backbone. By integrating contrastive learning with clustering, CueCo sets a new direction for advancing unsupervised visual representation learning.
title Cluster Contrast for Unsupervised Visual Representation Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2507.12359