Single domain generalization aims to train a generalizable model with only one source
domain to perform well on arbitrary unseen target domains. Image augmentation based on …

Self-supervised representation learning in computer vision relies heavily on hand-crafted
image transformations to learn meaningful and invariant features. However few extensive …

Recent unsupervised representation learning methods rely heavily on various
transformations to generate distinctive views of given samples. Transformations for these …

Current contrastive learning methods use random transformations sampled from a large list
of transformations, with fixed hyper-parameters, to learn invariance from an unannotated …

Self-supervised representation learning (SSRL) in computer vision relies heavily on simple
image transformations such as random rotation, crops, or illumination to learn meaningful …

Contrastive Learning is a paradigm for learning representation functions that recover useful
similarity structure in a dataset based on samples of positive (similar) and negative …