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.