Random erasing in Computer Vision - Model Metrics & Evaluation

Metrics & Evaluation - Random erasing

Which metric matters for Random Erasing and WHY

Random erasing is a data augmentation method used in computer vision to improve model robustness. The key metrics to watch are validation accuracy and generalization performance. This means how well the model predicts on new, unseen images. Random erasing helps the model not rely on specific parts of an image, so accuracy on test data usually improves.

Also, watch training loss to ensure the model is learning well despite the added noise. If training loss stays reasonable and validation accuracy improves, random erasing is helping.

Confusion Matrix Example

Imagine a model classifying images into cats and dogs. After training with random erasing, the confusion matrix might look like this:

      | Predicted Cat | Predicted Dog |
      |---------------|---------------|
      | True Cat: 45  | 5             |
      | True Dog: 7   | 43            |
    

Here, TP (True Positives) for cats = 45, FP (False Positives) for cats = 5, FN (False Negatives) for cats = 7, and TN (True Negatives) for cats = 43.

Precision for cats = 45 / (45 + 5) = 0.9, Recall for cats = 45 / (45 + 7) = 0.865.

Precision vs Recall Tradeoff with Random Erasing

Random erasing can help improve recall by forcing the model to recognize objects even if parts are missing or occluded. This means the model misses fewer true objects.

However, if random erasing is too strong, it might confuse the model and lower precision, causing more false alarms.

For example, in a face recognition system, high recall means fewer missed faces (good for security). But too many false alarms (low precision) can annoy users. Random erasing helps balance this by making the model robust but not careless.

Good vs Bad Metric Values for Random Erasing

Good: Validation accuracy improves or stays stable compared to no augmentation. Precision and recall both increase or remain balanced. Training loss decreases steadily.

Bad: Validation accuracy drops significantly, or recall improves but precision drops too much. Training loss stays high or fluctuates wildly, showing the model struggles to learn.

Common Pitfalls with Metrics and Random Erasing

• Accuracy paradox: Accuracy might look good if the dataset is unbalanced, hiding poor recall on rare classes.
• Data leakage: If random erasing is applied incorrectly (e.g., on test data), metrics become unreliable.
• Overfitting indicators: If training accuracy is very high but validation accuracy is low, random erasing might not be helping or is too weak.
• Too aggressive erasing: Can harm learning and reduce all metrics.

Self Check

Your model trained with random erasing has 98% accuracy but only 12% recall on the rare class. Is it good for production?

Answer: No. The low recall means the model misses most examples of the rare class. Even with high accuracy, it fails at detecting important cases. Random erasing should help improve recall by making the model robust to missing parts, so you need to adjust augmentation strength or model design.

Key Result

Random erasing improves model robustness by increasing validation accuracy and recall while maintaining balanced precision.

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