PRIME: A Few Primitives Can Boost Robustness to Common Corruptions

Last update: Oct 30, 2022

Related tags

Overview

PRIME: A Few Primitives Can Boost Robustness to Common Corruptions

This is the official repository of PRIME, the data agumentation method introduced in the paper: "PRIME: A Few Primitives Can Boost Robustness to Common Corruptions". PRIME is a generic, plug-n-play data augmentation scheme that consists of simple families of max-entropy image transformations for conferring robustness to common corruptions. PRIME leads to significant improvements in corruption robustness on multiple benchmarks.

Pre-trained models

We provide different models trained with PRIME on CIFAR-10/100 and ImageNet datasets. You can download them from here.

Setup

This code has been tested with Python 3.8.5 and PyTorch 1.9.1. To install required dependencies run:

$ pip install -r requirements.txt

For corruption robustness evaluation, download and extract the CIFAR-10-C, CIFAR-100-C and ImageNet-C datasets from here.

Usage

We provide a script train.py for PRIME training on CIFAR-10/100, ImageNet-100 and ImageNet. For example, to train a ResNet-50 network on ImageNet with PRIME, run:

$ python -u train.py --config=config/imagenet_cfg.py \
    --config.save_dir=<save_dir> \
    --config.data_dir=<data_dir> \
    --config.cc_dir=<common_corr_dir> \
    --config.use_prime=True

Detailed configuration options can be found in config.

Results

Results on ImageNet/ImageNet-100 with a ResNet-50/ResNet-18 (†: without JSD loss)

Dataset	Method	Clean (↑)	CC Acc (↑)	mCE (↓)
ImageNet	Standard	76.1	38.1	76.1
ImageNet	AugMix	77.5	48.3	65.3
ImageNet	DeepAugment	76.7	52.6	60.4
ImageNet	PRIME†	77.0	55.0	57.5
ImageNet-100	Standard	88.0	49.7	100
ImageNet-100	AugMix	88.7	60.7	79.1
ImageNet-100	DeepAugment	86.3	67.7	68.1
ImageNet-100	PRIME	85.9	71.6	61.0

Results on CIFAR-10/100 with a ResNet-18

Dataset	Method	Clean (↑)	CC Acc (↑)	mCE (↓)
CIFAR-10	Standard	95.0	74.0	24.0
CIFAR-10	AugMix	95.2	88.6	11.4
CIFAR-10	PRIME	93.1	89.0	11.0
CIFAR-100	Standard	76.7	51.9	48.1
CIFAR-100	AugMix	78.2	64.9	35.1
CIFAR-100	PRIME	77.6	68.3	31.7

Citing this work

@article{PRIME2021,
    title = {PRIME: A Few Primitives Can Boost Robustness to Common Corruptions}, 
    author = {Apostolos Modas and Rahul Rade and Guillermo {Ortiz-Jim\'enez} and Seyed-Mohsen {Moosavi-Dezfooli} and Pascal Frossard},
    year = {2021},
    journal = {arXiv preprint arXiv:2112.13547}
}

Comments

Port to Kornia

Hi @amodas , just encountered your paper and it appears to be a very interesting augmentation.

I am wondering if you are interested in porting this code into Kornia? We are the maintainers of that project and hope to have this feature.

Let me know if anything!

/cc @edgarriba @ducha-aiki

opened by shijianjian 2

Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"

T-Few This repository contains the official code for the paper: "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learni

220 Dec 31, 2022

Official implementation of "Open-set Label Noise Can Improve Robustness Against Inherent Label Noise" (NeurIPS 2021)

Open-set Label Noise Can Improve Robustness Against Inherent Label Noise NeurIPS 2021: This repository is the official implementation of ODNL. Require

12 Dec 7, 2022

Implementation of Common Image Evaluation Metrics by Sayed Nadim (sayednadim.github.io). The repo is built based on full reference image quality metrics such as L1, L2, PSNR, SSIM, LPIPS. and feature-level quality metrics such as FID, IS. It can be used for evaluating image denoising, colorization, inpainting, deraining, dehazing etc. where we have access to ground truth.

Image Quality Evaluation Metrics Implementation of some common full reference image quality metrics. The repo is built based on full reference image q

10 Jan 1, 2023

Python wrapper class for OpenVINO Model Server. User can submit inference request to OVMS with just a few lines of code

Python wrapper class for OpenVINO Model Server. User can submit inference request to OVMS with just a few lines of code.

7 Jul 27, 2022

Consistency Regularization for Adversarial Robustness

Consistency Regularization for Adversarial Robustness Official PyTorch implementation of Consistency Regularization for Adversarial Robustness by Jiho

40 Dec 17, 2022

STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech

STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech Keon Lee, Ky

114 Dec 12, 2022

This is our ARTS test set, an enriched test set to probe Aspect Robustness of ABSA.

This is the repository for our 2020 paper "Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis". Data We provide

35 Nov 16, 2022

Official repository for Jia, Raghunathan, Göksel, and Liang, "Certified Robustness to Adversarial Word Substitutions" (EMNLP 2019)

Certified Robustness to Adversarial Word Substitutions This is the official GitHub repository for the following paper: Certified Robustness to Adversa

38 Oct 16, 2022

This is the dataset for testing the robustness of various VO/VIO methods

KAIST VIO dataset This is the dataset for testing the robustness of various VO/VIO methods You can download the whole dataset on KAIST VIO dataset Ind

1 Sep 1, 2022

PRIME: A Few Primitives Can Boost Robustness to Common Corruptions

Related tags

Overview

PRIME: A Few Primitives Can Boost Robustness to Common Corruptions

Pre-trained models

Setup

Usage

Results

Citing this work

You might also like...

Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"

Official implementation of "Open-set Label Noise Can Improve Robustness Against Inherent Label Noise" (NeurIPS 2021)

Python wrapper class for OpenVINO Model Server. User can submit inference request to OVMS with just a few lines of code

Consistency Regularization for Adversarial Robustness

STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech

This is our ARTS test set, an enriched test set to probe Aspect Robustness of ABSA.

Official repository for Jia, Raghunathan, Göksel, and Liang, "Certified Robustness to Adversarial Word Substitutions" (EMNLP 2019)

This is the dataset for testing the robustness of various VO/VIO methods

Comments

Port to Kornia

Owner

Apostolos Modas

Ready-to-use code and tutorial notebooks to boost your way into few-shot image classification.

Code for the paper "Benchmarking and Analyzing Point Cloud Classification under Corruptions"

Optimized primitives for collective multi-GPU communication

HashNeRF-pytorch - Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives

Boost learning for GNNs from the graph structure under challenging heterophily settings. (NeurIPS'20)

An algorithm study of the 6th iOS 10 set of Boost Camp Web Mobile

This project aim to create multi-label classification annotation tool to boost annotation speed and make it more easier.

Few-NERD: Not Only a Few-shot NER Dataset