Random erasing in Computer Vision

Introduction

Random erasing helps a computer see images better by hiding small parts randomly during training. This makes the computer learn to recognize objects even if parts are missing or covered.

When training a model to recognize objects in photos that might be partly blocked.

When you want to make your image recognition model stronger and less likely to make mistakes.

When you have a small set of images and want to create more variety without adding new pictures.

When you want to prevent your model from memorizing exact details and instead learn general features.

Syntax

Computer Vision

RandomErasing(p=0.5, scale=(0.02, 0.33), ratio=(0.3, 3.3), value=0, inplace=False)

p: chance to apply random erasing on an image during training.

scale and ratio control the size and shape of the erased area.

Examples

Randomly erases part of the image half of the time during training.

Computer Vision

RandomErasing(p=0.5)

Always erases a square patch between 10% and 20% of the image size, filling it with gray color (0.5).

Computer Vision

RandomErasing(p=1.0, scale=(0.1, 0.2), ratio=(1, 1), value=0.5)

Erases part of the image 30% of the time and modifies the image directly without making a copy.

Computer Vision

RandomErasing(p=0.3, inplace=True)

Sample Model

This code downloads a dog image, resizes it, converts it to a tensor, and applies random erasing with 100% chance. It erases a small square patch filled with zeros (black). Then it prints the shape and some pixel values from the erased area to show the effect.

Computer Vision

import torch
from torchvision import transforms
from PIL import Image
import requests
from io import BytesIO

# Load an example image
url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/2/26/YellowLabradorLooking_new.jpg/320px-YellowLabradorLooking_new.jpg'
response = requests.get(url)
img = Image.open(BytesIO(response.content)).convert('RGB')

# Define transform with Random Erasing
transform = transforms.Compose([
    transforms.Resize((128, 128)),
    transforms.ToTensor(),
    transforms.RandomErasing(p=1.0, scale=(0.1, 0.1), ratio=(1, 1), value=0)
])

# Apply transform
img_tensor = transform(img)

# Show tensor shape and a small part of tensor values
print(f"Image tensor shape: {img_tensor.shape}")
print(f"Sample pixel values at erased area (first 5 values): {img_tensor[:, 50:55, 50:55].flatten()[:5]}")

Important Notes

Random erasing is usually applied only during training, not when testing or using the model.

The erased area can be filled with zeros, random values, or the mean pixel value to simulate different occlusions.

Choosing the right probability and size of erasing is important to avoid hurting model performance.

Summary

Random erasing hides random parts of images during training to help models learn better.

It makes models more robust to missing or blocked parts in real images.

Use it as a simple way to improve image recognition without adding new data.

Practice

1. What is the main purpose of random erasing in computer vision training?

easy

A. To hide random parts of images to improve model robustness

B. To increase image resolution during training

C. To convert images to grayscale

D. To add noise to the entire image

Solution

1. Step 1: Understand random erasing concept

   Random erasing hides random parts of images during training to simulate missing or blocked areas.

2. Step 2: Identify the main goal

   This helps the model learn to recognize objects even if parts are missing, improving robustness.

3. Final Answer:

   To hide random parts of images to improve model robustness -> Option A

4. Quick Check:

   Random erasing = hiding parts for robustness [OK]

Hint: Random erasing hides parts, not changes resolution or color [OK]

Common Mistakes:

• Confusing random erasing with image resizing
• Thinking it adds noise to the whole image
• Believing it converts images to grayscale

2. Which of the following is the correct way to apply random erasing using PyTorch's torchvision transforms?

easy

A. transforms.RandomErase(p=0.5, scale=(0.02, 0.33), ratio=(0.3, 3.3))

B. transforms.RandomErased(p=0.5, scale=(0.02, 0.33), ratio=(0.3, 3.3))

C. transforms.RandomErasing(p=0.5, scale=(0.02, 0.33), ratio=(0.3, 3.3))

D. transforms.RandomEraseArea(p=0.5, scale=(0.02, 0.33), ratio=(0.3, 3.3))

Solution

1. Step 1: Recall PyTorch transform name

   The correct class name is RandomErasing in torchvision.transforms.

2. Step 2: Check method parameters

   Parameters like p, scale, and ratio are valid for RandomErasing.

3. Final Answer:

   transforms.RandomErasing(p=0.5, scale=(0.02, 0.33), ratio=(0.3, 3.3)) -> Option C

4. Quick Check:

   Correct class name and parameters = transforms.RandomErasing(p=0.5, scale=(0.02, 0.33), ratio=(0.3, 3.3)) [OK]

Hint: Remember exact class name: RandomErasing (no spaces or misspellings) [OK]

Common Mistakes:

• Misspelling the class name as RandomErase or RandomErased
• Using incorrect parameter names
• Confusing with other augmentation transforms

3. Consider this PyTorch code snippet applying random erasing:

import torch
import torchvision.transforms as transforms
transform = transforms.Compose([
    transforms.RandomErasing(p=1.0, scale=(0.9, 0.9), ratio=(1, 1))
])
image = torch.ones((3, 10, 10))
output = transform(image)
print(output[:, 4:6, 4:6])

What will be the printed output?

medium

A. An error because RandomErasing expects PIL images

B. A 3x2x2 tensor of zeros

C. A 3x2x2 tensor with random values

D. A 3x2x2 tensor of ones

Solution

1. Step 1: Understand RandomErasing behavior

   With p=1.0, random erasing always applies. The erased area is set to zero by default.

2. Step 2: Analyze scale and ratio

   Scale=(0.9, 0.9) and ratio=(1, 1) fix the erased area to 90% of image size (~9x9 block) at random location near edge.

3. Step 3: Check printed slice

   The printed slice output[:, 4:6, 4:6] (center 2x2) is always covered by the large erased area, so it will be zeros.

4. Final Answer:

   A 3x2x2 tensor of zeros -> Option B

5. Quick Check:

   RandomErasing sets erased area to zero [OK]

Hint: Erased area pixels become zero tensors [OK]

Common Mistakes:

• Assuming erased area keeps original values
• Thinking erased area has random noise
• Believing RandomErasing only works on PIL images

4. You wrote this code to apply random erasing but get an error:

transform = transforms.RandomErasing(p=0.5)
image = Image.open('cat.jpg')
output = transform(image)

What is the likely cause of the error?

medium

A. RandomErasing requires grayscale images only

B. The probability p must be 1.0

C. Image file path is incorrect

D. RandomErasing expects a tensor, not a PIL image

Solution

1. Step 1: Check input type for RandomErasing

   RandomErasing in torchvision expects a tensor input, not a PIL image.

2. Step 2: Identify missing transform step

   Missing transforms.ToTensor() before RandomErasing causes type error.

3. Final Answer:

   RandomErasing expects a tensor, not a PIL image -> Option D

4. Quick Check:

   RandomErasing input = tensor, not PIL [OK]

Hint: Always convert PIL image to tensor before RandomErasing [OK]

Common Mistakes:

• Passing PIL images directly to RandomErasing
• Assuming p must be 1.0 to work
• Thinking RandomErasing only works on grayscale

5. You want to improve your image classifier's robustness by combining random erasing with another augmentation. Which combination below is best practice?

hard

A. Use random erasing after converting images to tensors and normalize them

B. Apply random erasing before resizing images to fixed size

C. Apply random erasing on raw PIL images without any other transforms

D. Use random erasing only during testing, not training

Solution

1. Step 1: Understand transform order

   Random erasing requires tensor input, so it must come after ToTensor().

2. Step 2: Combine with normalization

   Normalization after tensor conversion is standard; random erasing fits well after these steps during training.

3. Step 3: Avoid applying random erasing before resizing or during testing

   Applying before resizing can cause errors; random erasing is a training augmentation only.

4. Final Answer:

   Use random erasing after converting images to tensors and normalize them -> Option A

5. Quick Check:

   Random erasing after ToTensor and normalize = best practice [OK]

Hint: Random erasing after ToTensor and normalize during training [OK]

Common Mistakes:

• Applying random erasing on raw PIL images
• Using random erasing during testing phase
• Applying random erasing before resizing images