[NeurIPS'21] "AugMax: Adversarial Composition of Random Augmentations for Robust Training" by Haotao Wang, Chaowei Xiao, Jean Kossaifi, Zhiding Yu, Animashree Anandkumar, and Zhangyang Wang.

Overview

AugMax: Adversarial Composition of Random Augmentations for Robust Training

License: MIT

Haotao Wang, Chaowei Xiao, Jean Kossaifi, Zhiding Yu, Anima Anandkumar, and Zhangyang Wang

In NeurIPS 2021

Overview

We propose AugMax, a data augmentation framework to unify the diversity and hardness. Being a stronger form of data augmentation, AugMax leads to a significantly augmented input distribution which makes model training more challenging. To solve this problem, we further design a disentangled normalization module, termed DuBIN (Dual-Batch-and-Instance Normalization) that disentangles the instance-wise feature heterogeneity arising from AugMax. AugMax-DuBIN leads to significantly improved out-of-distribution robustness, outperforming prior arts by 3.03%, 3.49%, 1.82% and 0.71% on CIFAR10-C, CIFAR100-C, Tiny ImageNet-C and ImageNet-C.

AugMax
AugMax achieves a unification between hard and diverse training samples.

results
AugMax achieves state-fo-the-art performance on CIFAR10-C, CIFAR100-C, Tiny ImageNet-C and ImageNet-C.

Training

AugMax-DuBIN training on <dataset> with <backbone>:

python augmax_training_ddp.py --gpu 0 --drp <data_root_path> --ds <dataset> --md <backbone> --Lambda 10

For example:

AugMax-DuBIN on CIFAR10 with ResNeXt29:

NCCL_P2P_DISABLE=1 python augmax_training_ddp.py --gpu 0 --drp /ssd1/haotao/datasets --ds cifar10 --md ResNeXt29 --Lambda 10

AugMax-DuBIN + DeepAug on ImageNet with ResNet18:

NCCL_P2P_DISABLE=1 python augmax_training_ddp.py --gpu 0 --drp /ssd1/haotao/datasets --ds IN --md ResNet18 --deepaug --Lambda 10 -e 30 --wd 1e-4 --decay multisteps --de 10 20 --ddp --dist_url tcp://localhost:23456

Pretrained models

The pretrained models are available on Google Drive.

Testing

To test the model trained on <dataset> with <backbone> and saved to <ckpt_path>:

python test.py --gpu 0 --ds <dataset> --drp /ssd1/haotao/datasets --md <backbone> --mode all --ckpt_path <ckpt_path>

For example:

python test.py --gpu 0 --ds cifar10 --drp /ssd1/haotao/datasets --md ResNet18_DuBIN --mode all --ckpt_path augmax_training/cifar10/ResNet18_DuBIN/fat-1-untargeted-10-0.1_Lambda10-jsd4_e200-b256_sgd-lr0.1-m0.9-wd0.0005_cos

Citation

@inproceedings{wang2021augmax,
  title={AugMax: Adversarial Composition of Random Augmentations for Robust Training},
  author={Wang, Haotao and Xiao, Chaowei and Kossaifi, Jean and Yu, Zhiding and Anandkumar, Anima and Wang, Zhangyang},
  booktitle={NeurIPS},
  year={2021}
}
You might also like...
Adversarial-Information-Bottleneck - Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck (NeurIPS21) This repository is the official implementation of Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning (NeurIPS21).
This repository is the official implementation of Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning (NeurIPS21).

Core-tuning This repository is the official implementation of ``Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regular

Code for the ICML 2021 paper
Code for the ICML 2021 paper "Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation", Haoxiang Wang, Han Zhao, Bo Li.

Bridging Multi-Task Learning and Meta-Learning Code for the ICML 2021 paper "Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Trainin

This is the official PyTorch implementation of the paper
This is the official PyTorch implementation of the paper "TransFG: A Transformer Architecture for Fine-grained Recognition" (Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai, Changhu Wang, Alan Yuille).

TransFG: A Transformer Architecture for Fine-grained Recognition Official PyTorch code for the paper: TransFG: A Transformer Architecture for Fine-gra

We evaluate our method on different datasets (including ShapeNet, CUB-200-2011, and Pascal3D+) and achieve state-of-the-art results, outperforming all the other supervised and unsupervised methods and 3D representations, all in terms of performance, accuracy, and training time. This is the unofficial code of  Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes. which achieve state-of-the-art trade-off between accuracy and speed on cityscapes and camvid, without using inference acceleration and extra data Pre-trained BERT Models for Ancient and Medieval Greek, and associated code for LaTeCH 2021 paper titled -
Pre-trained BERT Models for Ancient and Medieval Greek, and associated code for LaTeCH 2021 paper titled - "A Pilot Study for BERT Language Modelling and Morphological Analysis for Ancient and Medieval Greek"

Ancient Greek BERT The first and only available Ancient Greek sub-word BERT model! State-of-the-art post fine-tuning on Part-of-Speech Tagging and Mor

An image base contains 490 images for learning (400 cars and 90 boats), and another 21 images for testingAn image base contains 490 images for learning (400 cars and 90 boats), and another 21 images for testing
An image base contains 490 images for learning (400 cars and 90 boats), and another 21 images for testingAn image base contains 490 images for learning (400 cars and 90 boats), and another 21 images for testing

SVM Données Une base d’images contient 490 images pour l’apprentissage (400 voitures et 90 bateaux), et encore 21 images pour fait des tests. Prétrait

Comments
  • I train ResNet18 in Cifar100

    I train ResNet18 in Cifar100

    I train ResNet18 in Cifar100 with augmax and without augmax but i find that i can got 77.5% accuracy without augmax ,while i can only got 76.3% with augmax, can u give some explainations?

    opened by dreamer121121 5
  • missing L(f(x ∗ ); θ), y)

    missing L(f(x ∗ ); θ), y)

    in the paper the total loss(equation 5) - 1/2[L(f(x∗); θ), y) + L(f(x); θ), y)] + λLc(x, x∗) but in the implementation you only use L(f(x); θ), y) + λLc(x, x∗). which is the correct equation?

    opened by yuval-neh 1
  • Use custom dataset

    Use custom dataset

    Hello, Thank you for this code it is really helpful. I have a question is it possible to use the same code with custom dataset? If so please tell me what to change. Best regards

    opened by Yahya222 1
  • Missing package - resnet_DuBN

    Missing package - resnet_DuBN

    Hi, first of all congratulations on your acceptance to NeurIPS 2021, I was checking the code and I saw that you are referencing the package models.cifar10.resnet_DuBN that is not in the repository.

    Could you please add it to make the code reproducible?

    opened by lorenzomammana 1
Owner
VITA
Visual Informatics Group @ University of Texas at Austin
VITA
[ICCV'2021] "SSH: A Self-Supervised Framework for Image Harmonization", Yifan Jiang, He Zhang, Jianming Zhang, Yilin Wang, Zhe Lin, Kalyan Sunkavalli, Simon Chen, Sohrab Amirghodsi, Sarah Kong, Zhangyang Wang

SSH: A Self-Supervised Framework for Image Harmonization (ICCV 2021) code for SSH Representative Examples Main Pipeline RealHM DataSet Google Drive Pr

VITA 86 Dec 2, 2022
"SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image", Dejia Xu, Yifan Jiang, Peihao Wang, Zhiwen Fan, Humphrey Shi, Zhangyang Wang

SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image [Paper] [Website] Pipeline Code Environment pip install -r requirements

VITA 250 Jan 5, 2023
[CVPR 2021] "The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models" Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Yang Zhang, Michael Carbin, Zhangyang Wang

The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models Codes for this paper The Lottery Tickets Hypo

VITA 59 Dec 28, 2022
[ICLR 2021] "Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective" by Wuyang Chen, Xinyu Gong, Zhangyang Wang

Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective [PDF] Wuyang Chen, Xinyu Gong, Zhangyang Wang In ICLR 2

VITA 156 Nov 28, 2022
[ICLR 2021 Spotlight Oral] "Undistillable: Making A Nasty Teacher That CANNOT teach students", Haoyu Ma, Tianlong Chen, Ting-Kuei Hu, Chenyu You, Xiaohui Xie, Zhangyang Wang

Undistillable: Making A Nasty Teacher That CANNOT teach students "Undistillable: Making A Nasty Teacher That CANNOT teach students" Haoyu Ma, Tianlong

VITA 71 Dec 28, 2022
[CVPRW 21] "BNN - BN = ? Training Binary Neural Networks without Batch Normalization", Tianlong Chen, Zhenyu Zhang, Xu Ouyang, Zechun Liu, Zhiqiang Shen, Zhangyang Wang

BNN - BN = ? Training Binary Neural Networks without Batch Normalization Codes for this paper BNN - BN = ? Training Binary Neural Networks without Bat

VITA 40 Dec 30, 2022
[ICML 2021] “ Self-Damaging Contrastive Learning”, Ziyu Jiang, Tianlong Chen, Bobak Mortazavi, Zhangyang Wang

Self-Damaging Contrastive Learning Introduction The recent breakthrough achieved by contrastive learning accelerates the pace for deploying unsupervis

VITA 51 Dec 29, 2022
[ICML 2021] "Graph Contrastive Learning Automated" by Yuning You, Tianlong Chen, Yang Shen, Zhangyang Wang

Graph Contrastive Learning Automated PyTorch implementation for Graph Contrastive Learning Automated [talk] [poster] [appendix] Yuning You, Tianlong C

Shen Lab at Texas A&M University 80 Nov 23, 2022
[Preprint] "Chasing Sparsity in Vision Transformers: An End-to-End Exploration" by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang

Chasing Sparsity in Vision Transformers: An End-to-End Exploration Codes for [Preprint] Chasing Sparsity in Vision Transformers: An End-to-End Explora

VITA 64 Dec 8, 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

VITA 16 Nov 26, 2022