Towards Good Practices in Self-supervised Representation Learning
This work provides insights and best practices for researchers and practitioners working with self-supervised representation learning, particularly contrastive instance learning, to improve their understanding and application.
This paper investigates the underlying reasons for the success of contrastive instance learning in self-supervised representation learning. Through extensive empirical analysis, it aims to identify and document good practices that contribute to the strong performance of these methods.
Self-supervised representation learning has seen remarkable progress in the last few years. More recently, contrastive instance learning has shown impressive results compared to its supervised learning counterparts. However, even with the ever increased interest in contrastive instance learning, it is still largely unclear why these methods work so well. In this paper, we aim to unravel some of the mysteries behind their success, which are the good practices. Through an extensive empirical analysis, we hope to not only provide insights but also lay out a set of best practices that led to the success of recent work in self-supervised representation learning.