Domain Invariant Masked Autoencoders for Self-supervised Learning from Multi-domains. (arXiv:2205.04771v1 [cs.CV])

Generalizing learned representations across significantly different visual
domains is a fundamental yet crucial ability of the human visual system. While
recent self-supervised learning methods have achieved good performances with
evaluation set on the same domain as the training set, they will have an
undesirable performance decrease when tested on a different domain. Therefore,
the self-supervised learning from multiple domains task is proposed to learn
domain-invariant features that are not only suitable for evaluation on the same
domain as the training …

arxiv cv learning self-supervised learning supervised learning