Özet:

Although deep learning models have achieved great success in computer vision tasks such as image classification, object detection, image segmentation in the last decade, a large amount of labeled data requires in the training of these models, which are in a supervised learning approach. Therefore, in recent years, there has been an increased interest in self-supervised learning methods that can learn generalizable image representations by utilizing large-scale unlabeled data without the need for manually labeled data by humans. In this study, self-supervised learning methods used in computer vision tasks are comprehensively reviewed and categorization of self-supervised learning methods is provided. Performance comparisons of the reviewed self-supervised learning methods for image classification, object detection and image segmentation target tasks are presented. Finally, problematic issues in current methods are discussed and potential research topics are suggested for future studies.

Anahtar Kelimeler: