A Survey on Contrastive Self-Supervised Learning

Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. It is capable of adopting self-defined pseudolabels as supervision and use the learned representations for several downstream tasks. Specifically, contrastive learning has recently become a dominant component in self-supervised learning for computer vision, natural language processing (NLP), and other domains. It aims at embedding augmented versions of the same sample close to each other while trying to push away embeddings from different samples. This paper provides an extensive review of self-supervised methods that follow the contrastive approach. The work explains commonly used pretext tasks in a contrastive learning setup, followed by different architectures that have been proposed so far. Next, we present a performance comparison of different methods for multiple downstream tasks such as image classification, object detection, and action recognition. Finally, we conclude with the limitations of the current methods and the need for further techniques and future directions to make meaningful progress.

Automated summary

Self-supervised learning, particularly through contrastive learning, has gained popularity for its cost-effective approach in using self-defined pseudolabels for various downstream tasks. This paper extensively reviews self-supervised methods following the contrastive approach, explaining pretext tasks and different architectures used. Performance comparisons across multiple downstream tasks demonstrate variations in method effectiveness.