Why Random erasing in Computer Vision? - Purpose & Use Cases

The Big Idea

What if your model could learn to see through obstacles without extra data or effort?

The Scenario

Imagine you are teaching a computer to recognize objects in photos. You have many pictures, but some look very similar, and the computer gets confused. You try to add more pictures by manually editing them to cover parts of the objects, hoping the computer will learn better. This takes forever and is very tiring.

The Problem

Manually editing thousands of images to cover random parts is slow and boring. It's easy to make mistakes or miss important variations. Also, it's hard to cover enough different parts to help the computer learn well. This leads to poor results and wasted time.

The Solution

Random erasing automatically covers random parts of images during training. This tricks the computer into focusing on different features each time. It's fast, consistent, and creates many new variations without extra work. This helps the model learn to recognize objects even if parts are missing or hidden.

Before vs After

✗ Before

for img in images:
    manually_cover_part(img)
    train_model(img)

✓ After

for img in images:
    img = random_erasing(img)
    train_model(img)

What It Enables

Random erasing enables models to become more robust and accurate by learning from varied and partially hidden images automatically.

Real Life Example

In self-driving cars, random erasing helps the AI recognize pedestrians even if they are partly hidden behind objects like parked cars or trees.

Key Takeaways

Manual image editing for training is slow and error-prone.

Random erasing automatically creates useful image variations.

This improves model accuracy and robustness in real-world situations.

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