2024-07-15: Literature Reading and Paper Summary: Two Classical papers on contrastive learning
Contrastive learning models proposed in recent years (Figure 1 from A Simple Framework for Contrastive Learning of Visual Representations) Supervised learning has been widely used in machine learning, which requires the input data (for example, images) be annotated (for example, classes). We can use supervised learning to build models to find the relationship between input data and annotated labels and then use the models to predict labels for future inputs. This is the way in traditional machine learning, such as decision tree, logistic regression, SVM, and neural networks. It's costly to create annotations, and as a result for most of the circumstances annotation is not available . We need a method which can make use of tons of data in real life without annotation , which is called unsupervised learning . Conventional u nsupervised learning includes clustering (for example, k-means ), dimension reduction (for example, p rincipal component analysis ) and so...