This codebase is the official implementation of Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization (NeurIPS2021, Spotlight)

Related tags

Deep LearningT3A
Overview

Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization

This codebase is the official implementation of Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization (NeurIPS2021, Spotlight). This codebase is mainly based on DomainBed, with following modifications:

  • enable to use various backbone networks including Big Transfer (BiT), Vision Transformers (ViT, DeiT, HViT), and MLP-Mixer.
  • enable to test test-time adaptation method (T3A and Tent).

Installation

CUDA/Python

git clone [email protected]:matsuolab/Domainbed_contrib.git
cd Domainbed_contrib/docker
docker build -t {image_name} .
docker run -it -h `hostname` --runtime=nvidia -v /path/to/Domainbed_contrib /path/to/anyware --shm-size=40gb --name {container_name} {image_name}

Python libralies

We use pipenv for package management.

cd /path/to/Domainbed_contrib
pip install pipenv
pipenv install
pipenv shell
pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-1.8.0+cu102.html

Quick start

(1) Downlload the datasets

python -m domainbed.scripts.download --data_dir=/my/datasets/path --dataset pacs

Note: change --dataset pacs for downloading other datasets (e.g., vlcs, office_home, terra_incognita).

(2) Train a model on source domains

python -m domainbed.scripts.train\
       --data_dir /my/datasets/path\
       --output_dir /my/pretrain/path\
       --algorithm ERM\
       --dataset PACS\
       --hparams "{\"backbone\": \"resnet50\"}" 

This scripts will produce new directory /my/pretrain/path, which include the full training log.

Note: change --dataset PACS for training on other datasets (e.g., VLCS, OfficeHome, TerraIncognita).

Note: change --hparams "{\"backbone\": \"resnet50\"}" for using other backbones (e.g., resnet18, ViT-B16, HViT).

(3) Evaluate model with test time adaptation (Table 1, Table 2, Figure 2)

python -m domainbed.scripts.unsupervised_adaptation\
       --input_dir=/my/pretrain/path\
       --adapt_algorithm=T3A

This scripts will produce a new file in /my/pretrain/path, whose name is results_{adapt_algorithm}.jsonl.

Note: change --adapt_algorithm=T3A for using other test time adaptation methods (T3A, Tent, or TentClf).

(4) Evaluate model with fine-tuning classifier(Figure 1)

python -m domainbed.scripts.supervised_adaptation\
       --input_dir=/my/pretrain/path\
       --ft_mode=clf

This scripts will produce a new file in /my/pretrain/path, whose name is results_{ft_mode}.jsonl.

Available backbones

  • resnet18
  • resnet50
  • BiT-M-R50x3
  • BiT-M-R101x3
  • BiT-M-R152x2
  • ViT-B16
  • ViT-L16
  • DeiT
  • Hybrid ViT (HViT)
  • MLP-Mixer (Mixer-L16)

Reproducing results

Table 1 and Figure 2 (Tuned ERM and CORAL)

You can use scripts/hparam_search.sh. Specifically, for each dataset and base algorithm, you can just type a following command.

sh scripts/hparam_search.sh resnet50 PACS ERM

Note that, it automatically starts 240 jobs, and take many times to finish.

Table 2 and Figure 1 (ERM with various backbone)

You can use scripts/launch.sh. Specifically, for each backbone, you can just type following three commands.

sh scripts/launch.sh pretrain resnet50 10 3 local
sh scripts/launch.sh sup resnet50 10 3 local
sh scripts/launch.sh unsup resnet50 10 3 local

Other results

For table 1, we used scores reported by In Search of Lost Domain Generalization. Full results for the reported scores in LaTeX format available here. Note: We only used scores for VLCS, PACS, OfficeHome, and TerraIncognita. We used the resutls with IIDAccuracySelectionMethod.

License

This source code is released under the MIT license, included here.

Election Exit Poll Prediction and U.S.A Presidential Speech Analysis using Machine Learning

Machine_Learning Election Exit Poll Prediction and U.S.A Presidential Speech Analysis using Machine Learning This project is based on 2 case-studies:

Avnika Mehta 1 Jan 27, 2022
This repository contains the PyTorch implementation of the paper STaCK: Sentence Ordering with Temporal Commonsense Knowledge appearing at EMNLP 2021.

STaCK: Sentence Ordering with Temporal Commonsense Knowledge This repository contains the pytorch implementation of the paper STaCK: Sentence Ordering

Deep Cognition and Language Research (DeCLaRe) Lab 23 Dec 16, 2022
Bayesian regularization for functional graphical models.

BayesFGM Paper: Jiajing Niu, Andrew Brown. Bayesian regularization for functional graphical models. Requirements R version 3.6.3 and up Python 3.6 and

0 Oct 07, 2021
Torch code for our CVPR 2018 paper "Residual Dense Network for Image Super-Resolution" (Spotlight)

Residual Dense Network for Image Super-Resolution This repository is for RDN introduced in the following paper Yulun Zhang, Yapeng Tian, Yu Kong, Bine

Yulun Zhang 494 Dec 30, 2022
Temporally Efficient Vision Transformer for Video Instance Segmentation, CVPR 2022, Oral

Temporally Efficient Vision Transformer for Video Instance Segmentation Temporally Efficient Vision Transformer for Video Instance Segmentation (CVPR

Hust Visual Learning Team 203 Dec 31, 2022
A library of scripts that interact with the PythonTurtle module to create games, drawings, and more

TurtleLib TurtleLib is a library of scripts that interact with the PythonTurtle module to create games, drawings, and more! Using the Scripts Copy or

1 Jan 15, 2022
Simplified interface for TensorFlow (mimicking Scikit Learn) for Deep Learning

SkFlow has been moved to Tensorflow. SkFlow has been moved to http://github.com/tensorflow/tensorflow into contrib folder specifically located here. T

3.2k Dec 29, 2022
Multi-Glimpse Network With Python

Multi-Glimpse Network Our code requires Python ≥ 3.8 Installation For example, venv + pip: $ python3 -m venv env $ source env/bin/activate (env) $ pyt

9 May 10, 2022
Deeply Supervised, Layer-wise Prediction-aware (DSLP) Transformer for Non-autoregressive Neural Machine Translation

Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision Training Efficiency We show the training efficiency of our DSLP model b

Chenyang Huang 36 Oct 31, 2022
Pytorch Code for "Medical Transformer: Gated Axial-Attention for Medical Image Segmentation"

Medical-Transformer Pytorch Code for the paper "Medical Transformer: Gated Axial-Attention for Medical Image Segmentation" About this repo: This repo

Jeya Maria Jose 615 Dec 25, 2022
COPA-SSE contains crowdsourced explanations for the Balanced COPA dataset

COPA-SSE Repository for COPA-SSE: Semi-Structured Explanations for Commonsense Reasoning. COPA-SSE contains crowdsourced explanations for the Balanced

Ana Brassard 5 Jul 31, 2022
Robocop is your personal mini voice assistant made using Python.

Robocop-VoiceAssistant To use this project, you should have python installed in your system. If you don't have python installed, install it beforehand

Sohil Khanduja 3 Feb 26, 2022
Sparse R-CNN: End-to-End Object Detection with Learnable Proposals, CVPR2021

End-to-End Object Detection with Learnable Proposal, CVPR2021

Peize Sun 1.2k Dec 27, 2022
This is the pytorch re-implementation of the IterNorm

IterNorm-pytorch Pytorch reimplementation of the IterNorm methods, which is described in the following paper: Iterative Normalization: Beyond Standard

Lei Huang 32 Dec 27, 2022
A PyTorch implementation of the paper Mixup: Beyond Empirical Risk Minimization in PyTorch

Mixup: Beyond Empirical Risk Minimization in PyTorch This is an unofficial PyTorch implementation of mixup: Beyond Empirical Risk Minimization. The co

Harry Yang 121 Dec 17, 2022
This repository provides an efficient PyTorch-based library for training deep models.

s3sec Test AWS S3 buckets for read/write/delete access This tool was developed to quickly test a list of s3 buckets for public read, write and delete

Bytedance Inc. 123 Jan 05, 2023
Prometheus Exporter for data scraped from datenplattform.darmstadt.de

darmstadt-opendata-exporter Scrapes data from https://datenplattform.darmstadt.de and presents it in the Prometheus Exposition format. Pull requests w

Martin Weinelt 2 Apr 12, 2022
[ICML 2021] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning | 斗地主AI

[ICML 2021] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning DouZero is a reinforcement learning framework for DouDizhu (斗地主), t

Kwai Inc. 3.1k Jan 04, 2023
Delta Conformity Sociopatterns Analysis - Delta Conformity Sociopatterns Analysis

Delta_Conformity_Sociopatterns_Analysis ∆-Conformity is a local homophily measur

2 Jan 09, 2022
Implementation of the master's thesis "Temporal copying and local hallucination for video inpainting".

Temporal copying and local hallucination for video inpainting This repository contains the implementation of my master's thesis "Temporal copying and

David Álvarez de la Torre 1 Dec 02, 2022