A review on discriminative self-supervised learning methods

arXiv:2405.04969v1 Announce Type: new
Abstract: In the field of computer vision, self-supervised learning has emerged as a method to extract robust features from unlabeled data, where models derive labels autonomously from the data itself, without the need for manual annotation. This paper provides a comprehensive review of discriminative approaches of self-supervised learning within the domain of computer vision, examining their evolution and current status. Through an exploration of various methods including contrastive, self-distillation, knowledge distillation, feature decorrelation, and clustering techniques, …

abstract annotation arxiv computer computer vision cs.ai cs.cv data extract features labels paper review robust self-supervised learning supervised learning type vision