Random erasing in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the main purpose of random erasing in image data augmentation?

Random erasing is a technique used in training image models. What does it mainly help with?

A It helps the model learn to ignore small occlusions or missing parts in images, improving robustness.

B It increases the image resolution by adding random pixels.

C It converts images to grayscale to reduce color bias.

D It crops the image to a fixed size to standardize input.

💡 Hint

Think about how hiding parts of an image during training might help the model.

Random erasing hides random parts of an image during training. This forces the model to rely on other features and become more robust to occlusions or missing data.

❓ Predict Output

intermediate

What is the output shape after applying random erasing to a batch of images?

Given a batch of 16 RGB images of size 64x64, what will be the shape of the batch after applying random erasing augmentation?

Computer Vision

import torch
import torchvision.transforms as transforms

transform = transforms.Compose([
    transforms.RandomErasing(p=1.0, scale=(0.02, 0.33), ratio=(0.3, 3.3))
])

batch = torch.randn(16, 3, 64, 64)  # batch of 16 images
augmented_batch = torch.stack([transform(img) for img in batch])
print(augmented_batch.shape)

A torch.Size([16, 3, 64, 64])

B torch.Size([16, 3, 32, 32])

C torch.Size([16, 1, 64, 64])

D torch.Size([3, 64, 64])

💡 Hint

Random erasing modifies pixels but does not change image size or batch size.

Random erasing replaces a random rectangle area in each image with random values but keeps the original image size and batch size unchanged.

❓ Hyperparameter

advanced

Which hyperparameter controls the size of the erased area in random erasing?

In random erasing, which hyperparameter defines the proportion of the image area that can be erased?

A mean

B ratio

C p

D scale

💡 Hint

Think about which parameter sets the size range of the erased rectangle.

The 'scale' parameter controls the minimum and maximum proportion of the image area to erase. 'ratio' controls the aspect ratio of the erased rectangle, 'p' is the probability of applying erasing, and 'mean' is the pixel value used to fill the erased area.

❓ Metrics

advanced

How does random erasing typically affect model accuracy on test data?

When random erasing is applied during training, what is the usual effect on the model's accuracy on unseen test images?

A It usually decreases accuracy because it removes important image parts.

B It has no effect on accuracy since it only changes training images.

C It usually improves accuracy by making the model more robust to occlusions.

D It causes the model to overfit the training data.

💡 Hint

Consider how training with harder examples affects generalization.

Random erasing makes training images harder by hiding parts, which helps the model learn more general features and improves accuracy on new images.

🔧 Debug

expert

What error does this random erasing code raise?

Consider this code snippet using torchvision's RandomErasing. What error will it raise?

Computer Vision

import torchvision.transforms as transforms

transform = transforms.RandomErasing(p=1.0, scale=(0.5, 0.1))

# Applying transform to a tensor image
import torch
img = torch.randn(3, 32, 32)
transformed_img = transform(img)

A RuntimeError: input tensor must be 4D

B ValueError: scale should be a tuple (min, max) with min <= max

C TypeError: RandomErasing expects a PIL Image, not a tensor

D No error, code runs successfully

💡 Hint

Check the order of values in the scale tuple.

The 'scale' parameter must have the minimum value first and maximum second. Here, (0.5, 0.1) has min > max, causing a ValueError.

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