Cluster Contrast for Unsupervised Visual Representation Learning

TL;DR

CueCo is a new unsupervised visual representation learning method that combines contrastive learning and clustering to improve feature separation and compactness, achieving state-of-the-art results on several datasets.

Contribution

It introduces CueCo, a novel approach that integrates contrastive learning with clustering, enhancing unsupervised visual representation learning.

Findings

Achieves 91.40% top-1 accuracy on CIFAR-10

Achieves 68.56% top-1 accuracy on CIFAR-100

Achieves 78.65% top-1 accuracy on ImageNet-100

Abstract

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.