GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → perrying → realistic-ssl-evaluation-pytorch

perrying / realistic-ssl-evaluation-pytorch

Licence: MIT license
Reimplementation of "Realistic Evaluation of Deep Semi-Supervised Learning Algorithms"

Programming Languages

python
139335 projects - #7 most used programming language

Labels

deep-learningpytorchsemi-supervised-learning

Projects that are alternatives of or similar to realistic-ssl-evaluation-pytorch

Cleanlab
The standard package for machine learning with noisy labels, finding mislabeled data, and uncertainty quantification. Works with most datasets and models.
Stars: ✭ 2,526 (+3097.47%)
Mutual labels:  semi-supervised-learning
Cct
[CVPR 2020] Semi-Supervised Semantic Segmentation with Cross-Consistency Training.
Stars: ✭ 171 (+116.46%)
Mutual labels:  semi-supervised-learning
Improvedgan Pytorch
Semi-supervised GAN in "Improved Techniques for Training GANs"
Stars: ✭ 228 (+188.61%)
Mutual labels:  semi-supervised-learning
Uda
Unsupervised Data Augmentation (UDA)
Stars: ✭ 1,877 (+2275.95%)
Mutual labels:  semi-supervised-learning
Accel Brain Code
The purpose of this repository is to make prototypes as case study in the context of proof of concept(PoC) and research and development(R&D) that I have written in my website. The main research topics are Auto-Encoders in relation to the representation learning, the statistical machine learning for energy-based models, adversarial generation networks(GANs), Deep Reinforcement Learning such as Deep Q-Networks, semi-supervised learning, and neural network language model for natural language processing.
Stars: ✭ 166 (+110.13%)
Mutual labels:  semi-supervised-learning
Graph Adversarial Learning
A curated collection of adversarial attack and defense on graph data.
Stars: ✭ 188 (+137.97%)
Mutual labels:  semi-supervised-learning
Adversarial text
Code for Adversarial Training Methods for Semi-Supervised Text Classification
Stars: ✭ 109 (+37.97%)
Mutual labels:  semi-supervised-learning
DeFMO
[CVPR 2021] DeFMO: Deblurring and Shape Recovery of Fast Moving Objects
Stars: ✭ 144 (+82.28%)
Mutual labels:  semi-supervised-learning
Stylealign
[ICCV 2019]Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Transition
Stars: ✭ 172 (+117.72%)
Mutual labels:  semi-supervised-learning
Adversarial Autoencoders
Tensorflow implementation of Adversarial Autoencoders
Stars: ✭ 215 (+172.15%)
Mutual labels:  semi-supervised-learning
Adversarial Semisupervised Semantic Segmentation
Pytorch Implementation of "Adversarial Learning For Semi-Supervised Semantic Segmentation" for ICLR 2018 Reproducibility Challenge
Stars: ✭ 147 (+86.08%)
Mutual labels:  semi-supervised-learning
Deep Sad Pytorch
A PyTorch implementation of Deep SAD, a deep Semi-supervised Anomaly Detection method.
Stars: ✭ 152 (+92.41%)
Mutual labels:  semi-supervised-learning
Graph Representation Learning
Autoencoders for Link Prediction and Semi-Supervised Node Classification (DSAA 2018)
Stars: ✭ 199 (+151.9%)
Mutual labels:  semi-supervised-learning
Snowball
Implementation with some extensions of the paper "Snowball: Extracting Relations from Large Plain-Text Collections" (Agichtein and Gravano, 2000)
Stars: ✭ 131 (+65.82%)
Mutual labels:  semi-supervised-learning
Tricks Of Semi Superviseddeepleanring Pytorch
PseudoLabel 2013, VAT, PI model, Tempens, MeanTeacher, ICT, MixMatch, FixMatch
Stars: ✭ 240 (+203.8%)
Mutual labels:  semi-supervised-learning
Mixmatch Pytorch
Pytorch Implementation of the paper MixMatch: A Holistic Approach to Semi-Supervised Learning (https://arxiv.org/pdf/1905.02249.pdf)
Stars: ✭ 120 (+51.9%)
Mutual labels:  semi-supervised-learning
Vosk
VOSK Speech Recognition Toolkit
Stars: ✭ 182 (+130.38%)
Mutual labels:  semi-supervised-learning
Active-learning-for-object-detection
Active learning for deep object detection using YOLO
Stars: ✭ 35 (-55.7%)
Mutual labels:  semi-supervised-learning
Good Papers
I try my best to keep updated cutting-edge knowledge in Machine Learning/Deep Learning and Natural Language Processing. These are my notes on some good papers
Stars: ✭ 248 (+213.92%)
Mutual labels:  semi-supervised-learning
Triple Gan
See Triple-GAN-V2 in PyTorch: https://github.com/taufikxu/Triple-GAN
Stars: ✭ 203 (+156.96%)
Mutual labels:  semi-supervised-learning
View All Similar Projects ➔

realistic-ssl-evaluation-pytorch

This repository is reimplementation of Realistic Evaluation of Deep Semi-Supervised Learning Algorithms, by Avital Oliver*, Augustus Odena*, Colin Raffel*, Ekin D. Cubuk, and Ian J. Goodfellow, arXiv preprint arXiv:1804.09170. Original repo is here.

NOTE: This repository has been deprecated. Please see here, which includes UDA and FixMatch.

Requirements

  • Python 3.6+
  • PyTorch 1.1.0
  • torchvision 0.3.0
  • numpy 1.16.2

How to run

Prepare dataset

python build_dataset.py

Default setting is SVHN 1000 labels. If you try other settings, please check the options first by python build_dataset.py -h.

Running experiments

python train.py

Default setting is VAT. Please check the options by python python train.py -h

Performance

WIP

algorithm paper this repo
cifar10 4k labels svhn 1k labels cifar10 4k labels svhn 1k labels
Supervised 20.26 ±0.38 12.83 ±0.47 20.35±0.14 12.33±0.25
Pi-Model 16.37 ±0.63 7.19 ±0.27 16.24±0.38 7.81±0.39
Mean Teacher 15.87 ±0.28 5.65 ±0.47 15.77±0.22 6.48±0.44
VAT 13.86 ±0.27 5.63 ±0.20 13.83±0.49 5.84±0.20
VAT+EM 13.13 ±0.39 5.35 ±0.19 13.30±0.27 5.76±0.13
Pseudo-Label 17.78 ±0.57 7.62 ±0.29 N/A N/A
ICT ( 7.66 ±0.17 ) ( 3.53 ±0.07 ) N/A N/A
MixMatch ( 6.50 ) ( 3.27 ±0.31 ) N/A N/A

NOTE: Experimental setting of ICT and MixMatch papers is different from this benchmark.

Reference

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].