Official PyTorch implementation of the ICRA 2021 paper: Adversarial Differentiable Data Augmentation for Autonomous Systems.

Overview

Adversarial Differentiable Data Augmentation

This repository provides the official PyTorch implementation of the ICRA 2021 paper:

Adversarial Differentiable Data Augmentation for Autonomous Systems
Author: Manli Shu, Yu Shen, Ming C Lin, Tom Goldstein

Environment

The code has been tested on:

  • python == 3.7.9
  • pytorch == 1.10.0
  • torchvision == 0.8.2
  • kornia == 0.6.2
    More dependencies can be found at ./requirements.txt

Hardware requirements:

  • The default training and testing setting requires 1 GPU.

Data

Datasets appeared in our paper can be downloaded/generated by following the directions in this page.

Note: The "distortion" factor is added differently in our work, for which we cropped out the zero-padding around the distorted images. To reproduce the results in our paper, the same post-processing should be applied to the generated images with the "distortion" corruption:

python utils/cropping.py --dataset_root ${dataset_root} --dataset ${valData}

, where testing data with different corruptions are sorted in different folders under ${dataset_root} and ${valData} is the folder name of the original validation set without any corruption.

Training

  1. Set the ${dataset_root} and the ${dataset_name} arguments in ./scripts/train.sh. The "train" and "val" splits of the ${dataset_name} are supposed to be stored separatly under ${dataset_root}.
  2. Set the hyper-parameters for data augmentation in ./scripts/train.sh.
  3. Run:
    bash ./scripts/train.sh
    

Testing

  1. Set the paths to your dataset in ./scripts/test.sh
  2. exp_name: help locating the model checkpoint (should be one of the training exp).
  3. epoch: specify the model checkpoint
  4. Run:
    bash ./scripts/test.sh
    

Note that in the test script, we test the "combined" corrupting factor seperately, where we test a total of 25 random combination of corruptions. Test images with combined corrupting factors are generated on the fly, and we fix the random seed for reproducibility. (The randomly generated combination can be found in ./data/comb_param.txt. )

Citation

If you find the code or our method useful, please consider citing:

@InProceedings{shu2021advaug,
    author={Shu, Manli and Shen, Yu and Lin, Ming C. and Goldstein, Tom},
    title={Adversarial Differentiable Data Augmentation for Autonomous Systems}, 
    booktitle={2021 IEEE International Conference on Robotics and Automation (ICRA)}, 
    year={2021}
}
Owner
Manli
Manli
Learning hidden low dimensional dyanmics using a Generalized Onsager Principle and neural networks

OnsagerNet Learning hidden low dimensional dyanmics using a Generalized Onsager Principle and neural networks This is the original pyTorch implemenati

Haijun.Yu 3 Aug 24, 2022
Convert Apple NeuralHash model for CSAM Detection to ONNX.

Apple NeuralHash is a perceptual hashing method for images based on neural networks. It can tolerate image resize and compression.

Asuhariet Ygvar 1.5k Dec 31, 2022
PiRank: Learning to Rank via Differentiable Sorting

PiRank: Learning to Rank via Differentiable Sorting This repository provides a reference implementation for learning PiRank-based models as described

54 Dec 17, 2022
🔪 Elimination based Lightweight Neural Net with Pretrained Weights

ELimNet ELimNet: Eliminating Layers in a Neural Network Pretrained with Large Dataset for Downstream Task Removed top layers from pretrained Efficient

snoop2head 4 Jul 12, 2022
A python interface for training Reinforcement Learning bots to battle on pokemon showdown

The pokemon showdown Python environment A Python interface to create battling pokemon agents. poke-env offers an easy-to-use interface for creating ru

Haris Sahovic 184 Dec 30, 2022
GANSketchingJittor - Implementation of Sketch Your Own GAN in Jittor

GANSketching in Jittor Implementation of (Sketch Your Own GAN) in Jittor(计图). Or

Bernard Tan 10 Jul 02, 2022
PSML: A Multi-scale Time-series Dataset for Machine Learning in Decarbonized Energy Grids

PSML: A Multi-scale Time-series Dataset for Machine Learning in Decarbonized Energy Grids The electric grid is a key enabling infrastructure for the a

Texas A&M Engineering Research 19 Jan 07, 2023
Indonesian Car License Plate Character Recognition using Tensorflow, Keras and OpenCV.

Monopol Indonesian Car License Plate (Indonesia Mobil Nomor Polisi) Character Recognition using Tensorflow, Keras and OpenCV. Background This applicat

Jayaku Briliantio 3 Apr 07, 2022
MoCoPnet - Deformable 3D Convolution for Video Super-Resolution

Deformable 3D Convolution for Video Super-Resolution Pytorch implementation of l

Xinyi Ying 28 Dec 15, 2022
This dlib-based facial login system

Facial-Login-System This dlib-based facial login system is a technology capable of matching a human face from a digital webcam frame capture against a

Mushahid Ali 3 Apr 23, 2022
The implementation our EMNLP 2021 paper "Enhanced Language Representation with Label Knowledge for Span Extraction".

LEAR The implementation our EMNLP 2021 paper "Enhanced Language Representation with Label Knowledge for Span Extraction". See below for an overview of

杨攀 93 Jan 07, 2023
minimizer-space de Bruijn graphs (mdBG) for whole genome assembly

rust-mdbg: Minimizer-space de Bruijn graphs (mdBG) for whole-genome assembly rust-mdbg is an ultra-fast minimizer-space de Bruijn graph (mdBG) impleme

Barış Ekim 148 Dec 01, 2022
A Pytorch Implementation of Domain adaptation of object detector using scissor-like networks

A Pytorch Implementation of Domain adaptation of object detector using scissor-like networks Please follow Faster R-CNN and DAF to complete the enviro

2 Oct 07, 2022
Labels4Free: Unsupervised Segmentation using StyleGAN

Labels4Free: Unsupervised Segmentation using StyleGAN ICCV 2021 Figure: Some segmentation masks predicted by Labels4Free Framework on real and synthet

70 Dec 23, 2022
Image-to-image translation with conditional adversarial nets

pix2pix Project | Arxiv | PyTorch Torch implementation for learning a mapping from input images to output images, for example: Image-to-Image Translat

Phillip Isola 9.3k Jan 08, 2023
This repository contains the needed resources to build the HIRID-ICU-Benchmark dataset

HiRID-ICU-Benchmark This repository contains the needed resources to build the HIRID-ICU-Benchmark dataset for which the manuscript can be found here.

Biomedical Informatics at ETH Zurich 30 Dec 16, 2022
PyTorch code of my ICDAR 2021 paper Vision Transformer for Fast and Efficient Scene Text Recognition (ViTSTR)

Vision Transformer for Fast and Efficient Scene Text Recognition (ICDAR 2021) ViTSTR is a simple single-stage model that uses a pre-trained Vision Tra

Rowel Atienza 198 Dec 27, 2022
Implementation of C-RNN-GAN.

Implementation of C-RNN-GAN. Publication: Title: C-RNN-GAN: Continuous recurrent neural networks with adversarial training Information: http://mogren.

Olof Mogren 427 Dec 25, 2022
Source code for "UniRE: A Unified Label Space for Entity Relation Extraction.", ACL2021.

UniRE Source code for "UniRE: A Unified Label Space for Entity Relation Extraction.", ACL2021. Requirements python: 3.7.6 pytorch: 1.8.1 transformers:

Wang Yijun 109 Nov 29, 2022
Deep generative models of 3D grids for structure-based drug discovery

What is liGAN? liGAN is a research codebase for training and evaluating deep generative models for de novo drug design based on 3D atomic density grid

Matt Ragoza 152 Jan 03, 2023