Semi-Supervised Learning Demystified with PyTorch and SESEMI

How can we use the world’s seemingly endless supply of unlabeled data to help us solve supervised learning problems?

Artistic render of the “three spirals” synthetic dataset used in “Exploring Self-Supervised Regularization for Supervised and Semi-Supervised Learning”.

The biggest hurdle to clear when developing machine learning solutions has always been the data. Large-scale, clean, fully-annotated data sets like ImageNet and COCO…