{"id":13692978,"url":"https://github.com/zhunzhong07/Random-Erasing","last_synced_at":"2025-05-02T21:31:11.924Z","repository":{"id":44382176,"uuid":"103635160","full_name":"zhunzhong07/Random-Erasing","owner":"zhunzhong07","description":"Random Erasing Data Augmentation. Experiments on CIFAR10, CIFAR100 and Fashion-MNIST","archived":false,"fork":false,"pushed_at":"2023-11-08T12:56:54.000Z","size":16320,"stargazers_count":716,"open_issues_count":11,"forks_count":156,"subscribers_count":16,"default_branch":"master","last_synced_at":"2024-08-03T17:14:41.513Z","etag":null,"topics":["aaai2020","data-augmentation","image-classification","object-detection","person-re-identification","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zhunzhong07.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2017-09-15T08:45:42.000Z","updated_at":"2024-07-09T11:40:38.000Z","dependencies_parsed_at":"2022-07-14T13:20:51.011Z","dependency_job_id":"bb07c7a8-08d1-46b1-8c3d-879b62dc21f4","html_url":"https://github.com/zhunzhong07/Random-Erasing","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhunzhong07%2FRandom-Erasing","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhunzhong07%2FRandom-Erasing/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhunzhong07%2FRandom-Erasing/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhunzhong07%2FRandom-Erasing/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zhunzhong07","download_url":"https://codeload.github.com/zhunzhong07/Random-Erasing/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224337252,"owners_count":17294689,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["aaai2020","data-augmentation","image-classification","object-detection","person-re-identification","pytorch"],"created_at":"2024-08-02T17:01:04.111Z","updated_at":"2024-11-12T19:30:18.892Z","avatar_url":"https://github.com/zhunzhong07.png","language":"Python","funding_links":[],"categories":["Repos","Paper implementations｜论文实现","Paper implementations"],"sub_categories":["Other libraries｜其他库:","Other libraries:"],"readme":"# Random Erasing Data Augmentation\n===============================================================\n\n![Examples](all_examples-page-001.jpg)\n\n| black  | white | random |\n|----------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------|\n|![i1](img/001-black.gif)|![i2](img/001-white.gif)| ![i3](img/001-random.gif)|\n|![i4](img/002-black.gif)|![i5](img/002-white.gif)| ![i6](img/002-random.gif)|\n\n### This code has the source code for the paper \"[Random Erasing Data Augmentation](https://arxiv.org/abs/1708.04896)\".\n\nIf you find this code useful in your research, please consider citing:\n\n    @inproceedings{zhong2020random,\n    title={Random Erasing Data Augmentation},\n    author={Zhong, Zhun and Zheng, Liang and Kang, Guoliang and Li, Shaozi and Yang, Yi},\n    booktitle={Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},\n    year={2020}\n    }\n\n\n### Other re-implementations\n\n[\\[Official Torchvision in Transform\\]](https://pytorch.org/vision/stable/transforms.html#torchvision.transforms.RandomErasing)\n\n[\\[Pytorch: Random Erasing for ImageNet\\]](https://github.com/rwightman/pytorch-image-models)\n\n[\\[Python Augmentor\\]](http://augmentor.readthedocs.io/en/master/code.html#Augmentor.Pipeline.Pipeline.random_erasing)\n\n[\\[Person_reID CamStyle\\]](https://github.com/zhunzhong07/CamStyle)\n\n[\\[Person_reID_baseline + Random Erasing + Re-ranking\\]](https://github.com/layumi/Person_reID_baseline_pytorch)\n\n[\\[Keras re-implementation\\]](https://github.com/yu4u/cutout-random-erasing)\n\n\n### Installation\n\nRequirements for Pytorch （see [Pytorch](http://pytorch.org/) installation instructions）\n\n### Examples:\n\n#### CIFAR10\n\nResNet-20 baseline on CIFAR10：\n    ```\n    python cifar.py --dataset cifar10 --arch resnet --depth 20\n    ```\n    \nResNet-20 + Random Erasing on CIFAR10：\n    ```\n    python cifar.py --dataset cifar10 --arch resnet --depth 20 --p 0.5\n    ```\n\n#### CIFAR100\n\nResNet-20 baseline on CIFAR100：\n    ```\n    python cifar.py --dataset cifar100 --arch resnet --depth 20\n    ```\n    \nResNet-20 + Random Erasing on CIFAR100：\n    ```\n    python cifar.py --dataset cifar100 --arch resnet --depth 20 --p 0.5\n    ```\n\n#### Fashion-MNIST\n\n\nResNet-20 baseline on Fashion-MNIST：\n    ```\n    python fashionmnist.py --dataset fashionmnist --arch resnet --depth 20\n    ```\n    \nResNet-20 + Random Erasing on Fashion-MNIST：\n    ```\n    python fashionmnist.py --dataset fashionmnist --arch resnet --depth 20 --p 0.5\n    ```\n\n### Other architectures\n\nFor ResNet： \n    ```\n    --arch resnet --depth (20， 32， 44， 56， 110)\n    ```\n\nFor WRN：\n    ```\n    --arch wrn --depth 28 --widen-factor 10\n    ```\n\n### Our results\n\nYou can reproduce the results in our paper:\n\n| |  CIFAR10 | CIFAR10| CIFAR100 | CIFAR100| Fashion-MNIST | Fashion-MNIST|\n| -----   | -----  | ----  | -----  | ----  | -----  | ----  |\n|Models |  Base. | +RE | Base. | +RE | Base. | +RE |\n|ResNet-20 |  7.21 | 6.73 | 30.84 | 29.97 | 4.39 | 4.02 |\n|ResNet-32 |  6.41 | 5.66 | 28.50 | 27.18 | 4.16 | 3.80 |\n|ResNet-44 |  5.53 | 5.13 | 25.27 | 24.29 | 4.41 | 4.01 |\n|ResNet-56 |  5.31 | 4.89| 24.82 | 23.69 | 4.39 | 4.13 |\n|ResNet-110 |  5.10 | 4.61 | 23.73 | 22.10 | 4.40 | 4.01 |\n|WRN-28-10 |  3.80 | 3.08 | 18.49 | 17.73 | 4.01 | 3.65 |\n\n### 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](https://github.com/zhunzhong07/Random-Erasing/issues/9).\n\n\n\nIf you have any questions about this code, please do not hesitate to contact us.\n\n[Zhun Zhong](http://zhunzhong.site)\n\n[Liang Zheng](http://liangzheng.com.cn)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzhunzhong07%2FRandom-Erasing","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzhunzhong07%2FRandom-Erasing","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzhunzhong07%2FRandom-Erasing/lists"}