zhunzhong07 / Random Erasing
Licence: apache-2.0
Random Erasing Data Augmentation. Experiments on CIFAR10, CIFAR100 and Fashion-MNIST
Stars: ✭ 511
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Random Erasing
Awesome Computer Vision Models
A list of popular deep learning models related to classification, segmentation and detection problems
Stars: ✭ 278 (-45.6%)
Mutual labels: object-detection, image-classification
Lightnet
🌓 Bringing pjreddie's DarkNet out of the shadows #yolo
Stars: ✭ 322 (-36.99%)
Mutual labels: object-detection, image-classification
Autogluon
AutoGluon: AutoML for Text, Image, and Tabular Data
Stars: ✭ 3,920 (+667.12%)
Mutual labels: object-detection, image-classification
bird species classification
Supervised Classification of bird species 🐦 in high resolution images, especially for, Himalayan birds, having diverse species with fairly low amount of labelled data
Stars: ✭ 59 (-88.45%)
Mutual labels: image-classification, data-augmentation
Rectlabel Support
RectLabel - An image annotation tool to label images for bounding box object detection and segmentation.
Stars: ✭ 338 (-33.86%)
Mutual labels: object-detection, image-classification
general backbone
No description or website provided.
Stars: ✭ 37 (-92.76%)
Mutual labels: image-classification, data-augmentation
Neural Pipeline
Neural networks training pipeline based on PyTorch
Stars: ✭ 315 (-38.36%)
Mutual labels: object-detection, image-classification
Deep Learning With Python
Deep learning codes and projects using Python
Stars: ✭ 195 (-61.84%)
Mutual labels: object-detection, image-classification
Rexnet
Official Pytorch implementation of ReXNet (Rank eXpansion Network) with pretrained models
Stars: ✭ 319 (-37.57%)
Mutual labels: object-detection, image-classification
Face recognition
🍎 My own face recognition with deep neural networks.
Stars: ✭ 328 (-35.81%)
Mutual labels: object-detection, image-classification
Computer Vision Guide
📖 This guide is to help you understand the basics of the computerized image and develop computer vision projects with OpenCV. Includes Python, Java, JavaScript, C# and C++ examples.
Stars: ✭ 244 (-52.25%)
Mutual labels: object-detection, image-classification
Pba
Efficient Learning of Augmentation Policy Schedules
Stars: ✭ 461 (-9.78%)
Mutual labels: data-augmentation, image-classification
Catalyst
Accelerated deep learning R&D
Stars: ✭ 2,804 (+448.73%)
Mutual labels: object-detection, image-classification
pytorch-ricap
PyTorch implementation of RICAP (Random Image Cropping And Patching)
Stars: ✭ 40 (-92.17%)
Mutual labels: image-classification, data-augmentation
Syndata Generation
Code used to generate synthetic scenes and bounding box annotations for object detection. This was used to generate data used in the Cut, Paste and Learn paper
Stars: ✭ 214 (-58.12%)
Mutual labels: object-detection, data-augmentation
Alturos.yolo
C# Yolo Darknet Wrapper (real-time object detection)
Stars: ✭ 308 (-39.73%)
Mutual labels: object-detection, image-classification
Torchdistill
PyTorch-based modular, configuration-driven framework for knowledge distillation. 🏆18 methods including SOTA are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy.
Stars: ✭ 177 (-65.36%)
Mutual labels: object-detection, image-classification
Deepdetect
Deep Learning API and Server in C++14 support for Caffe, Caffe2, PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE
Stars: ✭ 2,306 (+351.27%)
Mutual labels: object-detection, image-classification
Involution
[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator
Stars: ✭ 252 (-50.68%)
Mutual labels: object-detection, image-classification
Sianet
An easy to use C# deep learning library with CUDA/OpenCL support
Stars: ✭ 353 (-30.92%)
Mutual labels: object-detection, image-classification
Random Erasing Data Augmentation
===============================================================
| black | white | random |
|---|---|---|
 |
 |
 |
 |
 |
 |
This code has the source code for the paper "Random Erasing Data Augmentation".
If you find this code useful in your research, please consider citing:
@inproceedings{zhong2020random,
title={Random Erasing Data Augmentation},
author={Zhong, Zhun and Zheng, Liang and Kang, Guoliang and Li, Shaozi and Yang, Yi},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
year={2020}
}
Other re-implementations
[Official Torchvision in Transform]
[Pytorch: Random Erasing for ImageNet]
[Person_reID_baseline + Random Erasing + Re-ranking]
Installation
Requirements for Pytorch （see Pytorch installation instructions）
Examples:
CIFAR10
ResNet-20 baseline on CIFAR10：
python cifar.py --dataset cifar10 --arch resnet --depth 20
ResNet-20 + Random Erasing on CIFAR10：
python cifar.py --dataset cifar10 --arch resnet --depth 20 --p 0.5
CIFAR100
ResNet-20 baseline on CIFAR100：
python cifar.py --dataset cifar100 --arch resnet --depth 20
ResNet-20 + Random Erasing on CIFAR100：
python cifar.py --dataset cifar100 --arch resnet --depth 20 --p 0.5
Fashion-MNIST
ResNet-20 baseline on Fashion-MNIST：
python fashionmnist.py --dataset fashionmnist --arch resnet --depth 20
ResNet-20 + Random Erasing on Fashion-MNIST：
python fashionmnist.py --dataset fashionmnist --arch resnet --depth 20 --p 0.5
Other architectures
For ResNet：
--arch resnet --depth (20， 32， 44， 56， 110)
For WRN：
--arch wrn --depth 28 --widen-factor 10
Our results
You can reproduce the results in our paper:
| CIFAR10 | CIFAR10 | CIFAR100 | CIFAR100 | Fashion-MNIST | Fashion-MNIST | |
|---|---|---|---|---|---|---|
| Models | Base. | +RE | Base. | +RE | Base. | +RE |
| ResNet-20 | 7.21 | 6.73 | 30.84 | 29.97 | 4.39 | 4.02 |
| ResNet-32 | 6.41 | 5.66 | 28.50 | 27.18 | 4.16 | 3.80 |
| ResNet-44 | 5.53 | 5.13 | 25.27 | 24.29 | 4.41 | 4.01 |
| ResNet-56 | 5.31 | 4.89 | 24.82 | 23.69 | 4.39 | 4.13 |
| ResNet-110 | 5.10 | 4.61 | 23.73 | 22.10 | 4.40 | 4.01 |
| WRN-28-10 | 3.80 | 3.08 | 18.49 | 17.73 | 4.01 | 3.65 |
NOTE THAT, if you use the latest released Fashion-MNIST, the performance of Baseline and RE will slightly lower than the results reported in our paper. Please refer to the issue.
If you have any questions about this code, please do not hesitate to contact us.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].