CrossNorm and SelfNorm for Generalization under Distribution Shifts (ICCV 2021)

Related tags

Deep Learning natural-language-processing computer-vision normalization domain-adaptation domain-generalization model-robustness
Overview

CrossNorm (CN) and SelfNorm (SN) (Accepted at ICCV 2021)

This is the official PyTorch implementation of our CNSN paper, in which we propose CrossNorm (CN) and SelfNorm (SN), two simple, effective, and complementary normalization techniques to improve generalization robustness under distribution shifts. 

@article{tang2021cnsn,
  title={CrossNorm and SelfNorm for Generalization under Distribution Shifts},
  author={Zhiqiang Tang, Yunhe Gao, Yi Zhu, Zhi Zhang, Mu Li, Dimitris Metaxas},
  journal={arXiv preprint arXiv:2102.02811},
  year={2021}
}

Install dependencies

conda create --name cnsn python=3.7
conda activate cnsn
conda install numpy
conda install pytorch==1.2.0 torchvision==0.4.0 cudatoolkit=10.0 -c pytorch

Prepare datasets

  • Download CIFAR-10-C and CIFAR-100-C datasets with:

    mkdir -p ./data
curl -O https://zenodo.org/record/2535967/files/CIFAR-10-C.tar
curl -O https://zenodo.org/record/3555552/files/CIFAR-100-C.tar
tar -xvf CIFAR-100-C.tar -C data/
tar -xvf CIFAR-10-C.tar -C data/

  • Download ImageNet-C with:

    mkdir -p ./data/ImageNet-C
curl -O https://zenodo.org/record/2235448/files/blur.tar
curl -O https://zenodo.org/record/2235448/files/digital.tar
curl -O https://zenodo.org/record/2235448/files/noise.tar
curl -O https://zenodo.org/record/2235448/files/weather.tar
tar -xvf blur.tar -C data/ImageNet-C
tar -xvf digital.tar -C data/ImageNet-C
tar -xvf noise.tar -C data/ImageNet-C
tar -xvf weather.tar -C data/ImageNet-C

Usage

We have included sample scripts in cifar10-scripts, cifar100-scripts, and imagenet-scripts. For example, there are 5 scripts for CIFAR-100 and WideResNet:

  1. ./cifar100-scripts/wideresnet/run-cn.sh

  2. ./cifar100-scripts/wideresnet/run-sn.sh

  3. ./cifar100-scripts/wideresnet/run-cnsn.sh

  4. ./cifar100-scripts/wideresnet/run-cnsn-consist.sh (Use CNSN with JSD consistency regularization)

  5. ./cifar100-scripts/wideresnet/run-cnsn-augmix.sh (Use CNSN with AugMix)

Pretrained models

  • Pretrained ResNet-50 ImageNet classifiers are available:
  1. ResNet-50 + CN
  2. ResNet-50 + SN
  3. ResNet-50 + CNSN
  4. ResNet-50 + CNSN + IBN + AugMix.
  • Results of the above 4 ResNet-50 models on ImageNet:
+CN +SN +CNSN +CNSN+IBN+AugMix
Top-1 err 23.3 23.7 23.3 22.3
mCE 75.1 73.8 69.7 62.8
You might also like...
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-

null 22 Sep 22, 2022
This repo includes our code for evaluating and improving transferability in domain generalization (NeurIPS 2021)

Transferability for domain generalization This repo is for evaluating and improving transferability in domain generalization (NeurIPS 2021), based on

gordon 9 Nov 29, 2022
Unofficial Pytorch Lightning implementation of Contrastive Syn-to-Real Generalization (ICLR, 2021)

Unofficial Pytorch Lightning implementation of Contrastive Syn-to-Real Generalization (ICLR, 2021)

Gyeongjae Choi 17 Sep 23, 2021
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)

S2-BNN (Self-supervised Binary Neural Networks Using Distillation Loss) This is the official pytorch implementation of our paper: "S2-BNN: Bridging th

Zhiqiang Shen 52 Dec 24, 2022
Official code for the paper: Deep Graph Matching under Quadratic Constraint (CVPR 2021)

QC-DGM This is the official PyTorch implementation and models for our CVPR 2021 paper: Deep Graph Matching under Quadratic Constraint. It also contain

Quankai Gao 55 Nov 14, 2022
Regularizing Generative Adversarial Networks under Limited Data (CVPR 2021)
Regularizing Generative Adversarial Networks under Limited Data (CVPR 2021)

Regularizing Generative Adversarial Networks under Limited Data [Project Page][Paper] Implementation for our GAN regularization method. The proposed r

Google 148 Nov 18, 2022
Implementation of
Implementation of "Distribution Alignment: A Unified Framework for Long-tail Visual Recognition"(CVPR 2021)

Implementation of "Distribution Alignment: A Unified Framework for Long-tail Visual Recognition"(CVPR 2021)

null 105 Nov 7, 2022
Code for EMNLP 2021 paper Contrastive Out-of-Distribution Detection for Pretrained Transformers.

Contra-OOD Code for EMNLP 2021 paper Contrastive Out-of-Distribution Detection for Pretrained Transformers. Requirements PyTorch Transformers datasets

Wenxuan Zhou 27 Oct 28, 2022
Adaout is a practical and flexible regularization method with high generalization and interpretability

Adaout Adaout is a practical and flexible regularization method with high generalization and interpretability. Requirements python 3.6 (Anaconda versi

lambett 1 Feb 9, 2022
Comments
  • For the segmentation experiment

    For the segmentation experiment

    Thanks for sharing your great paper and code. I am a student studying domain generalization in the semantic segmentation task. There was a generalization experiment (in table 4) in GTA5 -> Cityscapes in the CNSN paper, but I can't find it in this repository at this time. Could you please share the source code for this part?([email protected]) If it is difficult to share, please tell me in detail about the FCN8s network structure. And I wonder if the performance of the CNSN in Table 4 is the result of using domain randomization. Thanks for reading.

    opened by Genie-Kim 2
Owner
null
GitHub
PyTorch evaluation code for Delving Deep into the Generalization of Vision Transformers under Distribution Shifts.

Out-of-distribution Generalization Investigation on Vision Transformers This repository contains PyTorch evaluation code for Delving Deep into the Gen

Chongzhi Zhang 72 Dec 13, 2022
A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.

WILDS is a benchmark of in-the-wild distribution shifts spanning diverse data modalities and applications, from tumor identification to wildlife monitoring to poverty mapping.

P-Lambda 437 Dec 30, 2022
Pytorch implementation for "Adversarial Robustness under Long-Tailed Distribution" (CVPR 2021 Oral)

Adversarial Long-Tail This repository contains the PyTorch implementation of the paper: Adversarial Robustness under Long-Tailed Distribution, CVPR 20

Tong WU 89 Dec 15, 2022
The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We significantly improve the systematic generalization of transformer models on a variety of datasets using simple tricks and careful considerations.

Codebase for training transformers on systematic generalization datasets. The official repository for our EMNLP 2021 paper The Devil is in the Detail:

Csordás Róbert 57 Nov 21, 2022
Official PyTorch implementation of the Fishr regularization for out-of-distribution generalization

Fishr: Invariant Gradient Variances for Out-of-distribution Generalization Official PyTorch implementation of the Fishr regularization for out-of-dist

null 62 Dec 22, 2022
Official repository for CVPR21 paper "Deep Stable Learning for Out-Of-Distribution Generalization".

StableNet StableNet is a deep stable learning method for out-of-distribution generalization. This is the official repo for CVPR21 paper "Deep Stable L

null 120 Dec 28, 2022
Codebase for Amodal Segmentation through Out-of-Task andOut-of-Distribution Generalization with a Bayesian Model

Codebase for Amodal Segmentation through Out-of-Task andOut-of-Distribution Generalization with a Bayesian Model

Yihong Sun 12 Nov 15, 2022
PrimitiveNet: Primitive Instance Segmentation with Local Primitive Embedding under Adversarial Metric (ICCV 2021)

PrimitiveNet Source code for the paper: Jingwei Huang, Yanfeng Zhang, Mingwei Sun. [PrimitiveNet: Primitive Instance Segmentation with Local Primitive

Jingwei Huang 47 Dec 6, 2022
The Official Implementation of the ICCV-2021 Paper: Semantically Coherent Out-of-Distribution Detection.

SCOOD-UDG (ICCV 2021) This repository is the official implementation of the paper: Semantically Coherent Out-of-Distribution Detection Jingkang Yang,

Jake YANG 62 Nov 21, 2022
Distributionally robust neural networks for group shifts

Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization This code implements the g

null 151 Dec 25, 2022