The Illustrated FixMatch for Semi-Supervised Learning
Learn how to leverage unlabeled data using FixMatch for semi-supervised learning
semi-supervised-learning computer-vision pytorch illustrated tutorial
Resource links
Details
Objectives & Highlights

• Understand rationale behind semi-supervised learning • Know working mechanism of FixMatch and how it achieved 78% accuracy on CIFAR-10 with just 10 labeled images • Learn about RandAugment, CTAugment, Consistency Regularization and Pseudo-Labeling

Don't forget to tag @amitness in your comment.

Authors
T-shaped Machine Learning Engineer applying research to products.
Share this project
Similar projects
Semi-supervised image classification with GANs
Shows how to perform semi-supervised image classification with GANs. The cover image is from Chapter 7, GANs in Action.
Semixup: In- and Out-of-Manifold Regularization
Semixup is a semi-supervised learning method based on in/out-of-manifold regularization.
MedCAT - Medical Concept Annotation Tool
A tool used to extract information from Electronic Health Records (EHRs) and link it to biomedical ontologies like SNOMED-CT and UMLS.
Positive and Unlabeled Materials Machine Learning
PUMML is a code that uses semi-supervised machine learning to classify materials from only positive and unlabeled examples.