Jul 15, 2018 · We apply DeepCluster to the unsupervised training of convolutional neural networks on large datasets like ImageNet and YFCC100M. The resulting model outperforms …

In this paper, we propose an online algorithm, SwAV, that takes advantage of con-trastive methods without requiring to compute pairwise comparisons.

In this work, we present DeepCluster, a clus-tering method that jointly learns the parameters of a neural network and the cluster assignments of the resulting features. DeepCluster it-eratively …

Jul 15, 2024 · In this work, we propose ExCB, a framework that tackles this problem with a novel cluster balancing method. ExCB estimates the relative size of the clusters across batches and …

Nov 23, 2024 · In this work, we propose ExCB, a framework that tackles this problem with a novel cluster balancing method. ExCB estimates the relative size of the clusters across batches and …

This study introduces a novel representation learning method to enhance unsupervised deep clustering in Human Activity Recognition (HAR). Traditional unsupervised deep clustering …

Apr 11, 2025 · Multiview clustering (MVC) aims to integrate multiple related but different views of data to achieve more accurate clustering performance. Contrastive learning has found many …

Apr 17, 2025 · For unsupervised visual representation learning 23,24,25, some research efforts have also shown that it is beneficial to construct dynamic dictionaries, which are continually …

May 24, 2021 · Cluster discrimination is an effective pretext task for unsupervised representation learning, which often consists of two phases: clustering and discrimination. Clustering is to …

Joint clustering and feature learning methods have shown remarkable performance in unsupervised represen-tation learning. However, the training schedule alternating between …