Balancing Principle for Unsupervised Domain Adaptation

Related tags

Deep Learning bpda

Overview

Blancing Principle for Domain Adaptation

NeurIPS 2021 Paper

Abstract

We address the unsolved algorithm design problem of choosing a justified regularization parameter in unsupervised domain adaptation. This problem is intriguing as no labels are available in the target domain. Our approach starts with the observation that the widely-used approach of minimizing the source error, weighted by a distance measure between source and target feature representations, shares characteristics with regularized ill-posed inverse problems. Regularization parameters in inverse problems can be chosen by the fundamental principle of balancing approximation and sampling errors. We use this principle to balance learning errors and domain distance in a target error bound. As a result, we obtain a theoretically justified rule for the choice of the regularization parameter. In contrast to the state of the art, our approach allows source and target distributions with disjoint supports. An empirical comparative study on benchmark datasets underpins the performance of our approach.

Installing

Clone repository

git clone https://github.com/Xpitfire/bpda
cd bpda

Create a python 3 conda environment

conda env create -f environment.yml

Install package

pip install -e .

Ensure that all required temp directories are available

tmp
runs
data

Compute Results

Train domain adaptation method with balancing principle by calling the bp configs:

CUDA_VISIBLE_DEVICES=<device-id> PYTHONPATH=. python scripts/train.py --config configs/<your-bp-config>.json

# running a CMD experiment with BP
CUDA_VISIBLE_DEVICES=0 PYTHONPATH=. python scripts/train.py --config configs/config.minidomainnet_bp_cmd.json.json
# running a MMD experiment with BP
CUDA_VISIBLE_DEVICES=0 PYTHONPATH=. python scripts/train.py --config configs/config.minidomainnet_bp_mmd.json.json

Evaluate results Set the respective base_dir and method setting in the viz/results_extractor_MiniDomainNet.py file and run:

PYTHONPATH=. python viz/results_extractor_MiniDomainNet.py

References

@article{Zellinger:21,
  title={The balancing principle for parameter choice in distance-regularized domain adaptation},
  author={Werner Zellinger and Natalia Shepeleva and Marius-Constantin Dinu and Hamid Eghbal-zadeh and Ho\'an Nguyen Duc and Bernhard Nessler and Sergei V.~Pereverzyev and Bernhard A. Moser},
  journal={NeurIPS},
  year={2021}
}

Comments

CVE-2007-4559 Patch

Patching CVE-2007-4559

Hi, we are security researchers from the Advanced Research Center at Trellix. We have began a campaign to patch a widespread bug named CVE-2007-4559. CVE-2007-4559 is a 15 year old bug in the Python tarfile package. By using extract() or extractall() on a tarfile object without sanitizing input, a maliciously crafted .tar file could perform a directory path traversal attack. We found at least one unsantized extractall() in your codebase and are providing a patch for you via pull request. The patch essentially checks to see if all tarfile members will be extracted safely and throws an exception otherwise. We encourage you to use this patch or your own solution to secure against CVE-2007-4559. Further technical information about the vulnerability can be found in this blog.

If you have further questions you may contact us through this projects lead researcher Kasimir Schulz.

opened by TrellixVulnTeam 0

[CVPR2021] Domain Consensus Clustering for Universal Domain Adaptation

[CVPR2021] Domain Consensus Clustering for Universal Domain Adaptation [Paper] Prerequisites To install requirements: pip install -r requirements.txt

84 Dec 26, 2022

A Pytorch Implementation of [Source data‐free domain adaptation of object detector through domain

A Pytorch Implementation of Source data‐free domain adaptation of object detector through domain‐specific perturbation Please follow Faster R-CNN and

1 Dec 25, 2021

Code for the paper "Balancing Training for Multilingual Neural Machine Translation, ACL 2020"

Balancing Training for Multilingual Neural Machine Translation Implementation of the paper Balancing Training for Multilingual Neural Machine Translat

21 May 18, 2022

PyTorch implementation of the paper Deep Networks from the Principle of Rate Reduction

Deep Networks from the Principle of Rate Reduction This repository is the official PyTorch implementation of the paper Deep Networks from the Principl

459 Dec 27, 2022

Official NumPy Implementation of Deep Networks from the Principle of Rate Reduction (2021)

Deep Networks from the Principle of Rate Reduction This repository is the official NumPy implementation of the paper Deep Networks from the Principle

49 Dec 16, 2022

Re-implementation of the Noise Contrastive Estimation algorithm for pyTorch, following "Noise-contrastive estimation: A new estimation principle for unnormalized statistical models." (Gutmann and Hyvarinen, AISTATS 2010)

Noise Contrastive Estimation for pyTorch Overview This repository contains a re-implementation of the Noise Contrastive Estimation algorithm, implemen

42 Nov 24, 2022

Learning hidden low dimensional dyanmics using a Generalized Onsager Principle and neural networks

OnsagerNet Learning hidden low dimensional dyanmics using a Generalized Onsager Principle and neural networks This is the original pyTorch implemenati

3 Aug 24, 2022

[CVPR 2022] "The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy" by Tianlong Chen, Zhenyu Zhang, Yu Cheng, Ahmed Awadallah, Zhangyang Wang

The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy Codes for this paper: [CVPR 2022] The Pr

16 Nov 26, 2022

IJCAI2020 & IJCV 2020 :city_sunrise: Unsupervised Scene Adaptation with Memory Regularization in vivo

Seg_Uncertainty In this repo, we provide the code for the two papers, i.e., MRNet：Unsupervised Scene Adaptation with Memory Regularization in vivo, IJ

348 Jan 5, 2023

Balancing Principle for Unsupervised Domain Adaptation

Related tags

Overview

Blancing Principle for Domain Adaptation

NeurIPS 2021 Paper

Abstract

Installing

Compute Results

References

You might also like...

[CVPR2021] Domain Consensus Clustering for Universal Domain Adaptation

A Pytorch Implementation of [Source data‐free domain adaptation of object detector through domain

Code for the paper "Balancing Training for Multilingual Neural Machine Translation, ACL 2020"

PyTorch implementation of the paper Deep Networks from the Principle of Rate Reduction

Official NumPy Implementation of Deep Networks from the Principle of Rate Reduction (2021)

Re-implementation of the Noise Contrastive Estimation algorithm for pyTorch, following "Noise-contrastive estimation: A new estimation principle for unnormalized statistical models." (Gutmann and Hyvarinen, AISTATS 2010)

Learning hidden low dimensional dyanmics using a Generalized Onsager Principle and neural networks

[CVPR 2022] "The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy" by Tianlong Chen, Zhenyu Zhang, Yu Cheng, Ahmed Awadallah, Zhangyang Wang

IJCAI2020 & IJCV 2020 :city_sunrise: Unsupervised Scene Adaptation with Memory Regularization in vivo

Comments

CVE-2007-4559 Patch

Patching CVE-2007-4559

Owner

Marius-Constantin Dinu

CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation

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

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

A PyTorch implementation for Unsupervised Domain Adaptation by Backpropagation(DANN), support Office-31 and Office-Home dataset

(CVPR2021) DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation

Unified unsupervised and semi-supervised domain adaptation network for cross-scenario face anti-spoofing, Pattern Recognition

IAST: Instance Adaptive Self-training for Unsupervised Domain Adaptation (ECCV 2020)

Code of TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation

Unsupervised Domain Adaptation for Nighttime Aerial Tracking (CVPR2022)

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