semi-supervised

A PyTorch-based Semi-Supervised Learning (SSL) Codebase for Pixel-wise (Pixel) Vision Tasks [ECCV 2020]

Code for <Confidence Regularized Self-Training> in ICCV19 (Oral)

ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation (CVPR20)

a transductive approach for video object segmentation

Tensorflow implementation of Semi-supervised Sequence Learning (https://arxiv.org/abs/1511.01432)

Simple sklearn based python implementation of Positive-Unlabeled (PU) classification using bagging based ensembles

PyTorch implementation of consistency regularization methods for semi-supervised learning

Official repository of the AAAI'2022 paper "GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection"

Code for our CVPR 2021 Paper "Self-Supervised Learning for Semi-Supervised Temporal Action Proposal".

Supplementary material for IJCNN paper "XGBOD: Improving Supervised Outlier Detection with Unsupervised Representation Learning"

Semi-supervised adversarial neural networks for classification of single cell transcriptomics data

Pytorch implementation of the Loc2Vec with some modifications for speed

code released for our CVPR 2021 paper "Domain Adaptation with Auxiliary Target Domain-Oriented Classifier"

A PyTorch implementation of VSumPtrGAN

Exploring the Limits of Low-Resource Neural Machine Translation

The implementation of "Semi-supervised Medical Image Classification with Global Latent Mixing". [MICCAI2020]

Multi-label classification based on timm, and add SimCLR to timm.

Semi supervised learning framework of Python.

Revisiting Consistency Regularization for Semi-supervised Change Detection in Remote Sensing Images

An official implementation of paper "Data-Uncertainty Guided Multi-Phase Learning for Semi-supervised Object Detection"

Memory Oriented Transfer Learning for Semi-Supervised Image Deraining

Weakly-supervised road-lane markings detection for autonomous driving, mitigating the lack of training data

ECHO is a semi-supervised framework for classifying evolving data streams based on our previous approach SAND. The most expensive module of SAND is the change detection module, which has cubic time complexity. ECHO uses dynamic programming to reduce the time complexity. Moreover, ECHO has a maximum allowable sliding window size. If there is no concept drift detected within this limit, ECHO updates the classifiers and resets the sliding window. Experiment results show that ECHO achieves significant speed up over SAND while maintaining similar accuracy. Please refer to the paper (mentioned in the reference section) for further details.

SAND: Semi-Supervised Adaptive Novel Class Detection and Classification over Data Stream

semi-supervised deep learning for classification of molecular structures

Separable Structure Modeling for Semi-supervised Video Object Segmentation

Python code for the semi-supervised learning method particle competition and cooperation

Simple graphical model for semi-supervised learning

Multi-Agent Generally Intelligent Simultaneous Training Algorithm for Project Zeta