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

Unsupervised representation learning with contrastive learning achieves great success
recently. However, these methods have to duplicate each training batch to construct …

By leveraging contrastive learning, clustering, and other pretext tasks, unsupervised
methods for learning image representations have reached impressive results on standard …

Contrastive learning methods for unsupervised visual representation learning have reached
remarkable levels of transfer performance. We argue that the power of contrastive learning …

In this paper, we propose a novel self-supervised representation learning by taking
advantage of a neighborhood-relational encoding (NRE) among the training data …

Unsupervised representation learning has achieved outstanding performances using
centralized data available on the Internet. However, the increasing awareness of privacy …

The recently advanced unsupervised learning approaches use the siamese-like framework
to compare two" views" from the same image for learning representations. Making the two …

Self-supervised learning (especially contrastive learning) has attracted great interest due to
its huge potential in learning discriminative representations in an unsupervised manner …

Over the last years, deep convolutional neural networks (ConvNets) have transformed the
field of computer vision thanks to their unparalleled capacity to learn high level semantic …

Unsupervised visual representation learning remains a largely unsolved problem in
computer vision research. Among a big body of recently proposed approaches for …