[Paper] Random Erasing (RE): Random Erasing Data Augmentation (Image Classification)

Improves Models for Image Classification, Object Detection & Person Re-identification

Random Erasing (From Author’s GitHub: https://github.com/zhunzhong07/Random-Erasing) Meow!

In this story, Random Erasing Data Augmentation (Random Erasing, RE), by Xiamen University, University of Technology Sydney, Australian National University, and Carnegie Mellon University, is shortly presented. In this paper:

  • Random Erasing is proposed to randomly select a rectangle region in an image and erases its pixels with random values.
  • This reduces the risk of overfitting and makes the model robust to occlusion.
  • It is is complementary to commonly used data augmentation techniques such as random cropping and flipping.

This is a paper in 2020 AAAI with over 600 citations. (Sik-Ho Tsang @ Medium)


  1. Random Erasing (RE)
  2. Ablation Study
  3. Experimental Results

1. Random Erasing (RE)

1.1. Random Erasing (RE) Algorithm

  • For an image I in a mini-batch, the probability of it undergoing Random Erasing is p.
  • Random Erasing randomly selects a rectangle region Ie in an image, and erases its pixels with random values.
  • The area of the image is S = W ×H. The area of erasing rectangle region is randomized as Se, where Se/S is in range specified by minimum sl and maximum sh.
  • The aspect ratio re of erasing rectangle region is randomly initialized between r1 and r2.
  • The size of Ie is:
  • and:
  • If xe+We W and ye+HeH, we set the region, Ie = (xe, ye, xe +We, ye +He), as the selected rectangle region.
  • With the selected erasing region Ie, each pixel in Ie is assigned to a random value in [0, 255].
  • The detailed RE algorithm is as below:
Random Erasing (RE) Algorithm

1.2. Random Erasing for Image Classification and Person Re-identification

  • In general, training data does not provide the location of the object. In this case, Random Erasing is performed on the whole image.

1.3. Random Erasing for Object Detection

  • There are 3 schemes.
  1. Image-aware Random Erasing (IRE): selecting erasing region on the whole image.
  2. Object-aware Random Erasing (ORE): selecting erasing regions in the bounding box of each object. if there are multiple objects in the image, Random Erasing is applied on each object separately.
  3. Image and object-aware Random Erasing (I+ORE): selecting erasing regions in both the whole image and each object bounding box.

1.4. Comparison with Random Cropping

  • Random cropping reduces the contribution of the background.
  • CNN can learn the model on the presence of parts of the object instead of focusing on the whole object.
  • Random Erasing retains the overall structure of the object, only occluding some parts of object. Areas are re-assigned with random values, which can be viewed as adding noise to the image.
  • They can be complementary to each other.

2. Ablation Study

2.1. The impact of hyper-parameters

Test errors (%) under different hyper-parameters on CIFAR-10 with using Pre-Activation ResNet-18
  • Pre-Activation ResNet-18 is used as baseline.
  • 3 hyperparameters to evaluate, i.e., the erasing probability p, the area ratio range of erasing region sl and sh, and the aspect ratio range of erasing region r1 and r2.
  • To simplify experiment, sl is fixed to 0.02, r1 = 1/r2 and evaluate p, sh, and r1.
  • p = 0.5, sh = 0.4 and r1 = 0.3 as the base setting, and alter one of them.
  • When p ∈ [0.2, 0.8] and sh ∈ [0.2, 0.8], the average classification error rate is 4.48%, outperforming the baseline method (5.17%) by a large margin.
  • For aspect ratio, the best result are obtained when r1 = 0.3, error rate = 4.31%, reduces the classification error rate by 0.86% compared with the baseline.
  • p = 0.5, sl = 0.02, sh = 0.4, and r1 = 1/r2 = 0.3 as default settings.

2.2. Four Types of Random Values

Test errors (%) on CIFAR-10
  1. RE-R: Random value ranging in [0, 255].
  2. RE-M: mean ImageNet value.
  3. RE-0: 0.
  4. RE-255: 255.
  • RE-R achieves approximately equal performance to RE-M, RE-R is chosen.

3. Experimental Results

3.1. Image Classification

Test errors (%) with different architectures on CIFAR-10, CIFAR-100 and Fashion-MNIST
  • p = 0.5, sl = 0.02, sh = 0.4, and r1 = 1/r2 = 0.3.
  • For CIFAR-10, random erasing improves the accuracy by 0.49% using ResNet-110.
  • Random erasing obtains 3.08% error rate using WRN-28–10, which improves the accuracy by 0.72%.
  • For CIFAR-100, random erasing obtains 17.73% error rate which gains 0.76% than the WRN-28-10 baseline.
  • Random erasing improves WRN-28–10 from 4.01% to 3.65% in top-1 error on Fashion-MNIST.
Test errors (%) on ImageNet-2012 validation set
  • Random erasing consistently improves the results on all three ResNet variants on ImageNet.

3.2. Comparison with Dropout and Random Noise

Test errors (%) with different data augmentation methods on CIFAR-10
  • Applying Dropout or adding random noise at the image layer fails to improve the accuracy.

3.3. Comparing with Data Augmentation Methods

Test errors (%) with different data augmentation methods on CIFAR-10
  • RF: Random flipping, RC: Random cropping, RE: Random Erasing.
  • Random Erasing and the two competing techniques are complementary. Particularly, combining these three methods achieves 4.31% error rate, a 7% improvement over the baseline without any augmentation.

3.4. Robustness to Occlusion

Test Error Rates Against Different Occlusion Levels
  • The baseline performance drops quickly when increasing the occlusion level l.
  • Random erasing approach achieves 56.36% error rate when the occluded area is half of the image (l = 0.5), while the baseline rapidly drops to 75.04%.
  • Random Erasing improves the robustness of CNNs against occlusion.

3.5. Object Detection

VOC 2007 test detection average precision (%)
  • Faster R-CNN using VGG-16 backbone is used as baseline.
  • For Random Erasing, p = 0.5, sl = 0.02, sh = 0.2, and r1 = 1/r2=0.3.
  • The baseline got 69.1% mAP.
  • The detector training with I+ORE obtains further improved in performance with 71.5% mAP.
  • When using the enlarged 07+12 training set, 76.2% mAP is achieved.

3.6. Person Re-identification

Person re-identification performance with Random Erasing (RE) on Market-1501, DukeMTMC-reID, and CUHK03
  • For Random Erasing, p = 0.5, sl = 0.02, sh = 0.2, and r1 = 1/r2=0.3.
  • For Market-1501, Random Erasing improves the rank-1 by 3.10% and 2.67% for IDE and SVDNet with using ResNet-50.
  • For DukeMTMC-reID, Random Erasing increases the rank-1 accuracy from 71.99% to 74.24% for IDE (ResNet-50) and from 76.82% to 79.31% for SVDNet (ResNet-50).
  • For CUHK03, TriNet gains 8.28% and 5.0% in rank-1 accuracy when applying Random Erasing.
  • This indicates that Random erasing can reduce the risk of over-fitting and improves the re-ID performance.




PhD, Researcher. I share what I've learnt and done. :) My LinkedIn: https://www.linkedin.com/in/sh-tsang/, My Paper Reading List: https://bit.ly/33TDhxG

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

My AI Heroes During Corona Days

Cool AI programming tools in Python

Sentiment Analysis on iOS Using Swift, Natural Language, and Combine: Hacker News Top Stories

NLP Representations Techniques Part2

Machine Learning

An Introduction to Recurrent Neural Network

Micro-Outlier removal: climb high in Kaggle with minimum effort using this technique

Review — Ensemble-based Semi-supervised Learning to Improve Noisy Soiling Annotations in…

Developing Indonesian Traffic Sign Detection using Deep Convolutional Neural Network in Google…

Get the Medium app

Sik-Ho Tsang

Sik-Ho Tsang

PhD, Researcher. I share what I've learnt and done. :) My LinkedIn: https://www.linkedin.com/in/sh-tsang/, My Paper Reading List: https://bit.ly/33TDhxG

More from Medium

Review — ConvNeXt: A ConvNet for the 2020s

ViT — An Image is worth 16x16 words: Transformers for Image Recognition at scale — ICLR’21

Ch 9. Vision Transformer Part I— Introduction and Fine-Tuning in PyTorch

LOTR: Face Landmark Localization Using Localization Transformer