Pushing the limit of semi-supervised learning with the Unified Semi-supervised Learning Benchmark - Microsoft Research

Neural models give competitive results when trained with supervised learning using sufficient high-quality labeled data. For example, according to statistics from the Paperswithcode website, recent traditional supervised learning methods can achieve an accuracy of over 88% on the ImageNet dataset, which contains millions of data. However, acquiring large amounts of labeled data is often time-consuming […]

Pre-Trained Language Models and Their Applications - ScienceDirect

The Quiet Semi-Supervised Revolution, by Vincent Vanhoucke

A viable framework for semi-supervised learning on realistic dataset

Certainty driven consistency loss on multi-teacher networks for semi-supervised learning - ScienceDirect

Unified dual-label semi-supervised learning with top-k feature selection - ScienceDirect

Barlow Twins: Self-Supervised Learning

Deep learning in optical metrology: a review

Semi-Supervised Learning in Computer Vision

Semi-Supervised Learning in Computer Vision