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 […]

Semi-supervised learning (SSL) - A systematic survey — Anastasios Kyrillidis

Unveiling the Power of Semi-Supervised Learning: The Unified Semi-Supervised Learning Benchmark, by Jindong Wang, PyTorch

A survey on data‐efficient algorithms in big data era, Journal of Big Data

Principle of semi-supervised learning: 1) a model (e.g., CSP+LDA

Advancing Biosensors with Machine Learning

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

Beginner Guide of Semi-Supervised Learning

CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation

Google Brain's SimCLRv2 Achieves New SOTA in Semi-Supervised Learning