Understand and Improve Contrastive Learning Methods for Visual Representation: A Review
This is a review paper, so it is incremental, summarizing existing research rather than presenting new findings.
The paper reviews contrastive learning methods for visual representation, addressing the limitations of supervised learning such as dependency on labeled data and poor generalization, and highlights that contrastive learning has achieved state-of-the-art performance in several fields.
Traditional supervised learning methods are hitting a bottleneck because of their dependency on expensive manually labeled data and their weaknesses such as limited generalization ability and vulnerability to adversarial attacks. A promising alternative, self-supervised learning, as a type of unsupervised learning, has gained popularity because of its potential to learn effective data representations without manual labeling. Among self-supervised learning algorithms, contrastive learning has achieved state-of-the-art performance in several fields of research. This literature review aims to provide an up-to-date analysis of the efforts of researchers to understand the key components and the limitations of self-supervised learning.