Contrastive Learning is self-supervised representation learning by training a model to
differentiate between similar and dissimilar samples. It has been shown to be effective and …

Federated learning shows a bright promise as a privacy-preserving collaborative learning
technique. However, prevalent solutions mainly focus on all private data sampled from the …

Although self-/un-supervised methods have led to rapid progress in visual representation
learning, these methods generally treat objects and scenes using the same lens. In this …

Self-Supervised Learning (SSL) is a new paradigm for learning discriminative
representations without labeled data, and has reached comparable or even state-of-the-art …

Negative sampling has swiftly risen to prominence as a focal point of research, with wide-
ranging applications spanning machine learning, computer vision, natural language …

While large pretrained foundation models (FMs) have shown remarkable zero-shot
classification robustness to dataset-level distribution shifts, their robustness to subpopulation …

Self-supervised learning allows AI systems to learn effective representations from large
amounts of data using tasks that do not require costly labeling. Mode collapse, ie, the model …

Contrastive learning (CL) has been the de facto technique for self-supervised representation
learning (SSL), with impressive empirical success such as multi-modal representation …

Unsupervised domain adaptation (UDA) aims at learning a machine learning model using a
labeled source domain that performs well on a similar yet different, unlabeled target domain …

We introduce CAN, a simple, efficient and scalable method for self-supervised learning of
visual representations. Our framework is a minimal and conceptually clean synthesis of (C) …