PRIME: A Few Primitives Can Boost Robustness to Common Corruptions

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}
}
D2Go is a toolkit for efficient deep learning

D2Go D2Go is a production ready software system from FacebookResearch, which supports end-to-end model training and deployment for mobile platforms. W

Facebook Research 744 Jan 04, 2023
Accuracy Aligned. Concise Implementation of Swin Transformer

Accuracy Aligned. Concise Implementation of Swin Transformer This repository contains the implementation of Swin Transformer, and the training codes o

FengWang 77 Dec 16, 2022
「PyTorch Implementation of AnimeGANv2」を用いて、生成した顔画像を元の画像に上書きするデモ

AnimeGANv2-Face-Overlay-Demo PyTorch Implementation of AnimeGANv2を用いて、生成した顔画像を元の画像に上書きするデモです。

KazuhitoTakahashi 21 Oct 18, 2022
Roadmap to becoming a machine learning engineer in 2020

Roadmap to becoming a machine learning engineer in 2020, inspired by web-developer-roadmap.

Chris Hoyean Song 1.7k Dec 29, 2022
Code for the bachelors-thesis flaky fault localization

Flaky_Fault_Localization Scripts for the Bachelors-Thesis: "Flaky Fault Localization" by Christian Kasberger. The thesis examines the usefulness of sp

Christian Kasberger 1 Oct 26, 2021
Cervix ROI Segmentation Using U-NET

Cervix ROI Segmentation Using U-NET Overview This code illustrate how to segment the ROI in cervical images using U-NET. The ROI here meant to include

Scotty Kwok 35 Sep 14, 2022
Large dataset storage format for Pytorch

H5Record Large dataset ( 100G, = 1T) storage format for Pytorch (wip) Support python 3 pip install h5record Why? Writing large dataset is still a

theblackcat102 43 Oct 22, 2022
Iterative Normalization: Beyond Standardization towards Efficient Whitening

IterNorm Code for reproducing the results in the following paper: Iterative Normalization: Beyond Standardization towards Efficient Whitening Lei Huan

Lei Huang 21 Dec 27, 2022
Offcial repository for the IEEE ICRA 2021 paper Auto-Tuned Sim-to-Real Transfer.

Offcial repository for the IEEE ICRA 2021 paper Auto-Tuned Sim-to-Real Transfer.

47 Jun 30, 2022
Deep motion generator collections

GenMotion GenMotion (/gen’motion/) is a Python library for making skeletal animations. It enables easy dataset loading and experiment sharing for synt

23 May 24, 2022
Learning Saliency Propagation for Semi-supervised Instance Segmentation

Learning Saliency Propagation for Semi-supervised Instance Segmentation PyTorch Implementation This repository contains: the PyTorch implementation of

Berkeley DeepDrive 68 Oct 18, 2022
A modular domain adaptation library written in PyTorch.

A modular domain adaptation library written in PyTorch.

Kevin Musgrave 225 Dec 29, 2022
Repository for the COLING 2020 paper "Explainable Automated Fact-Checking: A Survey."

Explainable Fact Checking: A Survey This repository and the accompanying webpage contain resources for the paper "Explainable Fact Checking: A Survey"

Neema Kotonya 42 Nov 17, 2022
Scalable Attentive Sentence-Pair Modeling via Distilled Sentence Embedding (AAAI 2020) - PyTorch Implementation

Scalable Attentive Sentence-Pair Modeling via Distilled Sentence Embedding PyTorch implementation for the Scalable Attentive Sentence-Pair Modeling vi

Microsoft 25 Dec 02, 2022
[CVPR'21] Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformation

Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformation Weixiang Yang, Qi Li, Wenxi Liu, Yuanlong Yu, Y

118 Dec 26, 2022
code for TCL: Vision-Language Pre-Training with Triple Contrastive Learning, CVPR 2022

Vision-Language Pre-Training with Triple Contrastive Learning, CVPR 2022 News (03/16/2022) upload retrieval checkpoints finetuned on COCO and Flickr T

187 Jan 02, 2023
An Image compression simulator that uses Source Extractor and Monte Carlo methods to examine the post compressive effects different compression algorithms have.

ImageCompressionSimulation An Image compression simulator that uses Source Extractor and Monte Carlo methods to examine the post compressive effects o

James Park 1 Dec 11, 2021
[ICLR 2021] Is Attention Better Than Matrix Decomposition?

Enjoy-Hamburger 🍔 Official implementation of Hamburger, Is Attention Better Than Matrix Decomposition? (ICLR 2021) Under construction. Introduction T

Gsunshine 271 Dec 29, 2022
Code for MSc Quantitative Finance Dissertation

MSc Dissertation Code ReadMe Sector Volatility Prediction Performance Using GARCH Models and Artificial Neural Networks Curtis Nybo MSc Quantitative F

2 Dec 01, 2022
Plenoxels: Radiance Fields without Neural Networks

Plenoxels: Radiance Fields without Neural Networks Alex Yu*, Sara Fridovich-Keil*, Matthew Tancik, Qinhong Chen, Benjamin Recht, Angjoo Kanazawa UC Be

Sara Fridovich-Keil 81 Dec 25, 2022