The official codes of "Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners".

Overview

SSL models are Strong UDA learners

highlights

Introduction

This is the official code of paper "Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners". It is based on pure PyTorch and presents the high effectiveness of SSL methods on UDA tasks. You can easily develop new algorithms, or readily apply existing algorithms. Codes for UDA methods and "UDA + SSL" are given in another project.

The currently supported algorithms include:

Semi-supervised learning for unsupervised domain adatation.
  • Semi-supervised learning by entropy minimization (Entropy Minimization, NIPS 2004)
  • Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks (Self-training, ICMLW 2013)
  • Temporal ensembling for semi-supervised learning (Pi-model, ICML 2017)
  • Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results (Mean-teacher, NIPS 2017)
  • Virtual adversarial training: a regularization method for supervised and semi-supervised learning (VAT, TPAMI 2018)
  • Mixmatch: A holistic approach to semi-supervised learning (MixMatch, NIPS 2019)
  • Unsupervised data augmentation for consistency training (UDA, NIPS 2020)
  • Fixmatch: Simplifying semi-supervised learning with consistency and confidence (FixMatch, NIPS 2020)

highlights

Installation

This implementation is based on the Transfer Learning Library. Please refer to 'requirements' for installation. Note that only "DistributedDataParallel" training is supported in the current branch.

Usage

We have examples in the directory examples. A typical usage is

# Train a FixMatch on Office-31 Amazon -> Webcam task using ResNet 50.
# Assume you have put the datasets under the path `args.datapath/office-31`, 
# or you are glad to download the datasets automatically from the Internet to this path. Please go to the dictionary ./examples, and run:
CUDA_VISIBLE_DEVICES=0,1,2,3 python ../main.py --use_ema --dist_url tcp://127.0.0.1:10013 --multiprocessing_distributed --regular_only_feature --p_cutoff 0.95 --seed 1  --epochs 30  --batchsize 32 --mu 7 --iters_per_epoch 250  --source A --target W  --method Fixmatch --save_dir ../log/Office31 --dataset Office31

In the directory examples, you can find all the necessary running scripts to reproduce the benchmarks with specified hyper-parameters. We don't provide the checkpoints since the training of each model is quick and there are too many tasks.

Contributing

Any pull requests or issues are welcome. Models of other SSL methods on UDA tasks are highly expected.

Citation

If you use this toolbox or benchmark in your research, please cite this project.

@inproceedings{SSL2UDA,
  author = {xxx},
  title = {Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners},
  year = {2021},
  publisher = {xxx},
  journal = {xxx},
}

Acknowledgment

We would like to thank Transfer Learning Library for their excellent contribution.

License

MIT License, the same to Transfer Learning Library.

Owner
Yabin Zhang
Yabin Zhang
Neon: an add-on for Lightbulb making it easier to handle component interactions

Neon Neon is an add-on for Lightbulb making it easier to handle component interactions. Installation pip install git+https://github.com/neonjonn/light

Neon Jonn 9 Apr 29, 2022
AI virtual gym is an AI program which can be used to exercise and can be used to see if we are doing the exercises

AI virtual gym is an AI program which can be used to exercise and can be used to see if we are doing the exercises

4 Feb 13, 2022
Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"

T-Few This repository contains the official code for the paper: "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learni

220 Dec 31, 2022
This repository contains the implementation of the paper: Federated Distillation of Natural Language Understanding with Confident Sinkhorns

Federated Distillation of Natural Language Understanding with Confident Sinkhorns This repository provides an alternative method for ensembled distill

Deep Cognition and Language Research (DeCLaRe) Lab 11 Nov 16, 2022
General Multi-label Image Classification with Transformers

General Multi-label Image Classification with Transformers Jack Lanchantin, Tianlu Wang, Vicente Ordóñez Román, Yanjun Qi Conference on Computer Visio

QData 154 Dec 21, 2022
Irrigation controller for Home Assistant

Irrigation Unlimited This integration is for irrigation systems large and small. It can offer some complex arrangements without large and messy script

Robert Cook 176 Jan 02, 2023
This is the paddle code for SeBoW(Self-Born wiring for neural trees), a kind of neural tree born form a large search space

SeBoW: Self-Born Wiring for neural trees(PaddlePaddle version) This is the paddle code for SeBoW(Self-Born wiring for neural trees), a kind of neural

HollyLee 13 Dec 08, 2022
[NeurIPS 2021] Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods

Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods Large Scale Learning on Non-Homophilous Graphs: New Benchmark

60 Jan 03, 2023
Finite difference solution of 2D Poisson equation. Can handle Dirichlet, Neumann and mixed boundary conditions.

Poisson-solver-2D Finite difference solution of 2D Poisson equation Current version can handle Dirichlet, Neumann, and mixed (combination of Dirichlet

Mohammad Asif Zaman 34 Dec 23, 2022
Project repo for Learning Category-Specific Mesh Reconstruction from Image Collections

Learning Category-Specific Mesh Reconstruction from Image Collections Angjoo Kanazawa*, Shubham Tulsiani*, Alexei A. Efros, Jitendra Malik University

438 Dec 22, 2022
[NeurIPS '21] Adversarial Attacks on Graph Classification via Bayesian Optimisation (GRABNEL)

Adversarial Attacks on Graph Classification via Bayesian Optimisation @ NeurIPS 2021 This repository contains the official implementation of GRABNEL,

Xingchen Wan 12 Dec 23, 2022
People Interaction Graph

Gihan Jayatilaka*, Jameel Hassan*, Suren Sritharan*, Janith Senananayaka, Harshana Weligampola, et. al., 2021. Holistic Interpretation of Public Scenes Using Computer Vision and Temporal Graphs to Id

University of Peradeniya : COVID Research Group 1 Aug 24, 2022
Individual Treatment Effect Estimation

CAPE Individual Treatment Effect Estimation Run CAPE python train_causal.py --loop 10 -m cape_cau -d NI --i_t 1 Run a baseline model python train_cau

S. Deng 4 Sep 02, 2022
A Fast and Accurate One-Stage Approach to Visual Grounding, ICCV 2019 (Oral)

One-Stage Visual Grounding ***** New: Our recent work on One-stage VG is available at ReSC.***** A Fast and Accurate One-Stage Approach to Visual Grou

Zhengyuan Yang 118 Dec 05, 2022
A short and easy PyTorch implementation of E(n) Equivariant Graph Neural Networks

Simple implementation of Equivariant GNN A short implementation of E(n) Equivariant Graph Neural Networks for HOMO energy prediction. Just 50 lines of

Arsenii Senya Ashukha 97 Dec 23, 2022
Code for "R-GCN: The R Could Stand for Random"

RR-GCN: Random Relational Graph Convolutional Networks PyTorch Geometric code for the paper "R-GCN: The R Could Stand for Random" RR-GCN is an extensi

PreDiCT.IDLab 31 Sep 07, 2022
curl-impersonate: A special compilation of curl that makes it impersonate Chrome & Firefox

curl-impersonate A special compilation of curl that makes it impersonate real browsers. It can impersonate the four major browsers: Chrome, Edge, Safa

lwthiker 1.9k Jan 03, 2023
Implementation of the paper "Generating Symbolic Reasoning Problems with Transformer GANs"

Generating Symbolic Reasoning Problems with Transformer GANs This is the implementation of the paper Generating Symbolic Reasoning Problems with Trans

Reactive Systems Group 1 Apr 18, 2022
A PyTorch implementation of the Transformer model in "Attention is All You Need".

Attention is all you need: A Pytorch Implementation This is a PyTorch implementation of the Transformer model in "Attention is All You Need" (Ashish V

Yu-Hsiang Huang 7.1k Jan 04, 2023
GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation. (CVPR 2021)

GDR-Net This repo provides the PyTorch implementation of the work: Gu Wang, Fabian Manhardt, Federico Tombari, Xiangyang Ji. GDR-Net: Geometry-Guided

169 Jan 07, 2023