Official pytorch implement for “Transformer-Based Source-Free Domain Adaptation”

stanley

Last update: Dec 22, 2022

Related tags

Deep Learning TransDA

Overview

Official implementation for TransDA

Official pytorch implement for “Transformer-Based Source-Free Domain Adaptation”.

Overview:

Result:

Prerequisites:

python == 3.6.8
pytorch ==1.1.0
torchvision == 0.3.0
numpy, scipy, sklearn, PIL, argparse, tqdm

Prepare pretrain model

We choose R50-ViT-B_16 as our encoder.

wget https://storage.googleapis.com/vit_models/imagenet21k/R50+ViT-B_16.npz 
mkdir ./model/vit_checkpoint/imagenet21k 
mv R50+ViT-B_16.npz ./model/vit_checkpoint/imagenet21k/R50+ViT-B_16.npz

Our checkpoints could be find in Dropbox

Dataset:

Please manually download the datasets Office, Office-Home, VisDA, Office-Caltech from the official websites, and modify the path of images in each '.txt' under the folder './data/'.
The script "download_visda2017.sh" in data fold also can use to download visda

Training

Office-31

```python
sh run_office_uda.sh
```

Office-Home

```python
sh run_office_home_uda.sh
```

Office-VisDA

```python
sh run_visda.sh
```

Reference

ViT

TransUNet

SHOT

Code of TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation

TVT Code of TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation Datasets: Digit: MNIST, SVHN, USPS Object: Office, Office-Home, Vi

37 Dec 15, 2022

Pytorch implementation of four neural network based domain adaptation techniques: DeepCORAL, DDC, CDAN and CDAN+E. Evaluated on benchmark dataset Office31.

Deep-Unsupervised-Domain-Adaptation Pytorch implementation of four neural network based domain adaptation techniques: DeepCORAL, DDC, CDAN and CDAN+E.

49 Dec 20, 2022

code for our paper "Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer"

SHOT++ Code for our TPAMI submission "Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer" that is ext

75 Dec 16, 2022

STEM: An approach to Multi-source Domain Adaptation with Guarantees

STEM: An approach to Multi-source Domain Adaptation with Guarantees Introduction This is the official implementation of ``STEM: An approach to Multi-s

5 Dec 19, 2022

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

SSL models are Strong UDA learners Introduction This is the official code of paper "Semi-supervised Models are Strong Unsupervised Domain Adaptation L

26 Dec 26, 2022

Official implement of "CAT: Cross Attention in Vision Transformer".

CAT: Cross Attention in Vision Transformer This is official implement of "CAT: Cross Attention in Vision Transformer". Abstract Since Transformer has

100 Dec 15, 2022

Official implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer

Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer This repository contains the PyTorch code for Evo-ViT. This work proposes a slow-fas

53 Dec 5, 2022

Official pytorch implementation of "Feature Stylization and Domain-aware Contrastive Loss for Domain Generalization" ACMMM 2021 (Oral)

Feature Stylization and Domain-aware Contrastive Loss for Domain Generalization This is an official implementation of "Feature Stylization and Domain-

22 Sep 22, 2022

PyTorch code for the paper "Curriculum Graph Co-Teaching for Multi-target Domain Adaptation" (CVPR2021)

PyTorch code for the paper "Curriculum Graph Co-Teaching for Multi-target Domain Adaptation" (CVPR2021) This repo presents PyTorch implementation of M

79 Dec 19, 2022

Comments

Does this repo contain full code?

I notice that the model is not implemented as the paper depicts. And, is it feasible to train ResNetV2+ViT on a single gpu? I tried to run it on a 2080Ti, but it reported an "CUDA out of memory" error.

opened by tiangarin 5
About attention

Thanks for your work! Have you tried other attention modules instead of Transformer? And only add transformer improved 1% than SHOT baseline on Office31 in your paper's ablation study, can other attention module also improve? Thank you!

opened by ThomsonTang6 1

Official pytorch implement for “Transformer-Based Source-Free Domain Adaptation”

Related tags

Overview

Official implementation for TransDA

Overview:

Result:

Prerequisites:

Prepare pretrain model

Dataset:

Training

Office-31

Office-Home

Office-VisDA

Reference

You might also like...

Code of TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation

Pytorch implementation of four neural network based domain adaptation techniques: DeepCORAL, DDC, CDAN and CDAN+E. Evaluated on benchmark dataset Office31.

code for our paper "Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer"

STEM: An approach to Multi-source Domain Adaptation with Guarantees

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

Official implement of "CAT: Cross Attention in Vision Transformer".

Official implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer

Official pytorch implementation of "Feature Stylization and Domain-aware Contrastive Loss for Domain Generalization" ACMMM 2021 (Oral)

PyTorch code for the paper "Curriculum Graph Co-Teaching for Multi-target Domain Adaptation" (CVPR2021)

Comments

Does this repo contain full code?

About attention

Owner

stanley

A Pytorch Implementation of Source Data-free Domain Adaptation for a Faster R-CNN

CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation

CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation

Code to reproduce the experiments in the paper "Transformer Based Multi-Source Domain Adaptation" (EMNLP 2020)

code for ICCV 2021 paper 'Generalized Source-free Domain Adaptation'

Code for our NeurIPS 2021 paper 'Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation'

Adversarial Adaptation with Distillation for BERT Unsupervised Domain Adaptation

Third party Pytorch implement of Image Processing Transformer (Pre-Trained Image Processing Transformer arXiv:2012.00364v2)

Code for CVPR2021 "Visualizing Adapted Knowledge in Domain Transfer". Visualization for domain adaptation. #explainable-ai

[CVPR2021] Domain Consensus Clustering for Universal Domain Adaptation