The Mean Teacher Model is a popular approach for semi-supervised learning, where a student model learns from a more stable teacher model that updates through Exponential Moving Average (EMA). It helps improve consistency between predictions and provides a smoother training signal.

Code for "TriGAN-SiaMT: A Triple-Segmentor Adversarial Network with Bounding Box Priors for Semi-Supervised Brain Lesion Segmentation"

Experiments on some existing Re-ID methods on a different dataset with qualitative and quantitative analyses of their performance along with proposals to improve the results further.

This repository contains the complete implementation of a semi-supervised instance segmentation pipeline using YOLOv11. The project explores FixMatch, MixMatch, and Mean Teacher methods and evaluates their effectiveness using limited labeled data and abundant unlabeled data as part of the CSE 438 Final Project.

Semi supervised learning for semantic image segmentation

PyTorch-driven model for efficient vascular segmentation and classification using limited data. Combines semi-supervised and supervised techniques, setting a new standard in resource-efficient auto-segmentation.

Implementation of semi-supervised learning: UDA, MixMatch, Mean-teacher, focusing on NLP, powered by Pytorch

Mean Teacher-based Cross-Domain Activity Recognition using WiFi Signals, IoTJ 2023

RAIL: Region-Aware Instructive Learning for Semi-Supervised Tooth Segmentation in CBCT

Reproduce some methods in semi-supervised papers.

[NeurIPS2024 Spotlight] Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network