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 …

Learning on data represented with multiple views (eg, multiple types of descriptors or
modalities) is a rapidly growing direction in machine learning and computer vision. Although …

Self-supervision has emerged as a propitious method for visual representation learning after
the recent paradigm shift from handcrafted pretext tasks to instance-similarity based …

Self-supervised learning has recently achieved great success in representation learning
without human annotations. The dominant method–that is contrastive learning, is generally …

Self-supervised representation learning for visual pre-training has achieved remarkable
success with sample (instance or pixel) discrimination and semantics discovery of instance …

Recent self-supervised representation learning techniques have largely closed the gap
between supervised and unsupervised learning on ImageNet classification. While the …

Contrastive learning is a self-supervised representation learning method that achieves
milestone performance in various classification tasks. However, due to its unsupervised …

Deep clustering against self-supervised learning (SSL) is a very important and promising
direction for unsupervised visual representation learning since it requires little domain …

Recent works have advanced the performance of self-supervised representation learning by
a large margin. The core among these methods is intra-image invariance learning. Two …

Unsupervised approaches to learning in neural networks are of substantial interest for
furthering artificial intelligence, both because they would enable the training of networks …