Positive and unlabeled (PU) learning aims to train a suitable classifier simply based on a set of positive data and unlabeled data. The state-of-the-art methods usually formulate PU learning as a cost ...

Self-supervised learning is considered a part of machine learning which is helpful in such situations where we have data with unlabeled information. We can say that it is a process ... We use ...

The unlabeled samples can come from known or novel classes. The goal of OpenCon is to learn distinguishable representations of known and novel classes such that similar objects are grouped together.

It has been widely adopted in the deep learning community and is considered a promising approach for learning useful representations from unlabeled data. The main idea of this repository is to suggest ...

Contrastive learning uses different crops and variations of the same image to train ... though the images might not be annotated for supervised learning. “Unlabeled data is often available in ...

Researchers from Peking University have introduced a new semi-supervised learning framework that integrates various techniques to enhance MRI segmentation by leveraging unlabeled data. This ...