paper-with-me

Papers

Random Erasing Data Augmentation

2017-08-16 · Zhun Zhong, Liang Zheng, Guoliang Kang, Shaozi Li, Yi Yang

In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN). In training, Random Erasing randomly selects a rectangle region in an image and erases its pixels with random values. In this process, training images with various levels of occlusion are generated, which reduces the risk of over-fitting and makes the model robust to occlusion. Random Erasing is parameter learning free, easy to implement, and can be integrated with most of the CNN-based recognition models. Albeit simple, Random Erasing is complementary to commonly used data augmentation techniques such as random cropping and flipping, and yields consistent improvement over strong baselines in image classification, object detection and person re-identification. Code is available at: https://github.com/zhunzhong07/Random-Erasing.

📄 PDF Abstract BibTeX arXiv:1708.04896

Code (18)

zhunzhong07/Random-Erasing 공식 구현 pytorch
Brunogomes97/Imdb
CoinCheung/SphereReID pytorch
IyatomiLab/CE-CLCNN pytorch
Janghyeonwoong/Random-Erasing-Tensorflow2 tf
KentaItakura/CNN-classification-using-random-erasing-and-cut-out
NVlabs/DG-Net pytorch
PaddlePaddle/PaddleClas paddle
aditya30394/Person-Re-Identification pytorch
albumentations-team/albumentations pytorch
layumi/Person_reID_baseline_pytorch pytorch
layumi/University1652-Baseline pytorch
pytorch/vision pytorch
rickyHong/Random-erasing-Data-Augumentation-repl pytorch
rlagywns0213/cifar100_data_augmentation pytorch
rwightman/pytorch-image-models pytorch
sek788432/Microsoft-Cats-and-Dogs-Image-Classification
shawnyuen/DataAugmentationPaperCollection

Tasks

Data AugmentationGeneral ClassificationImage Augmentationimage-classificationImage Classificationobject-detectionObject DetectionPerson Re-IdentificationRobust Object Detection

Methods 이 논문이 사용한 방법론

Random Erasing Random Erasing is a data augmentation method for training the convolutional neural network (CNN), which randomly selects a rectangle region in an image and erases its pixels with…

Similar Papers 제목 키워드 기반

Piecing and Chipping: An effective solution for the information-erasing view generation in Self-supervised Learning

2021-09-29 · Jingwei Liu, Yi Gu, Shentong Mo, Zhun Sun 외

In self-supervised learning frameworks, deep networks are optimized to align different views of an instance that contains the similar visual semantic information. The views are generated by conducting series of data augm…

Data AugmentationSelf-Supervised Learning

Combined Image Data Augmentations diminish the benefits of Adaptive Label Smoothing

2025-07-22 · Georg Siedel, Ekagra Gupta, Weijia Shao, Silvia Vock 외 arxiv

Soft augmentation regularizes the supervised learning process of image classifiers by reducing label confidence of a training sample based on the magnitude of random-crop augmentation applied to it. This paper extends th…

Data Augmentation

Attention-Guided Erasing: A Novel Augmentation Method for Enhancing Downstream Breast Density Classification

2024-01-08 · Adarsh Bhandary Panambur, Hui Yu, Sheethal Bhat, Prathmesh Madhu 외

The assessment of breast density is crucial in the context of breast cancer screening, especially in populations with a higher percentage of dense breast tissues. This study introduces a novel data augmentation technique…

breast density classificationData AugmentationTransfer Learning

Data Augmentation Through Random Style Replacement

2025-04-14 · Qikai Yang, Cheng Ji, Huaiying Luo, Panfeng Li 외

In this paper, we introduce a novel data augmentation technique that combines the advantages of style augmentation and random erasing by selectively replacing image subregions with style-transferred patches. Our approach…

Data AugmentationStyle Transfer

Long Term Stock Prediction based on Financial Statements

2021-11-01 · journal 2021 11 · Shujia Liu

This paper proposes a model with LSTM and fully connected layers to predict long term stock trendings based on financial statements. Two data augmentation techniques are applied on structured data: 1) adding random noise…

Data AugmentationPredictionStock Prediction