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

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

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

Siamese networks have become a common structure in various recent models for
unsupervised visual representation learning. These models maximize the similarity between …

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

Recent single image unsupervised representation learning techniques show remarkable
success on a variety of tasks. The basic principle in these works is instance discrimination …

Bootstrap Your Own Latent (BYOL) is a self-supervised learning approach for image
representation. From an augmented view of an image, BYOL trains an online network to …

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 algorithms based on instance discrimination train encoders to be
invariant to pre-defined transformations of the same instance. While most methods treat …

Transfer learning has attracted a lot of attention in the past decade. One crucial research
issue in transfer learning is how to find a good representation for instances of different …