Image augmentation transforms in Computer Vision - Model Metrics & Evaluation

Metrics & Evaluation - Image augmentation transforms

Which metric matters for Image Augmentation Transforms and WHY

Image augmentation helps models learn better by showing more varied pictures. The key metrics to check if augmentation works are validation accuracy and validation loss. These show if the model is learning to recognize images well on new, unseen data. If augmentation is good, validation accuracy should improve or stay stable while training accuracy might be lower. This means the model is not just memorizing but generalizing better.

Confusion Matrix Example

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

      | Predicted Cat | Predicted Dog |
      |---------------|---------------|
      | 45 (TP)       | 5 (FN)        |
      | 3 (FP)        | 47 (TN)       |
    

Total samples = 45 + 5 + 3 + 47 = 100

Precision = 45 / (45 + 3) = 0.94

Recall = 45 / (45 + 5) = 0.90

F1 Score = 2 * (0.94 * 0.90) / (0.94 + 0.90) ≈ 0.92

Precision vs Recall Tradeoff with Image Augmentation

Augmentation can help balance precision and recall. For example:

• High precision: The model rarely mistakes dogs for cats, so predictions are trustworthy.
• High recall: The model finds most cats, even if some dogs are wrongly labeled as cats.

If augmentation is too weak, recall might be low because the model misses varied cat images. If augmentation is too strong or unrealistic, precision might drop because the model gets confused.

Good vs Bad Metric Values for Image Augmentation

Good: Validation accuracy close to training accuracy, high F1 score (above 0.85), and balanced precision and recall.

Bad: Large gap between training and validation accuracy (overfitting), low recall (missing many true images), or very low precision (many wrong predictions).

Common Pitfalls in Metrics for Image Augmentation

• Accuracy paradox: High accuracy but poor recall if classes are imbalanced (e.g., many dog images, few cat images).
• Data leakage: Augmented images too similar to training images can inflate validation scores falsely.
• Overfitting indicators: Training accuracy very high but validation accuracy low, meaning augmentation is not helping generalization.

Self-Check Question

Your model trained with image augmentation has 98% training accuracy but only 60% validation accuracy. What does this mean?

Answer: The model is overfitting. It learned the training images too well but cannot generalize to new images. The augmentation might be too weak or not diverse enough to help the model learn general features.

Key Result

Validation accuracy and F1 score best show if image augmentation helps the model generalize well.

Practice

1. What is the main purpose of image augmentation in training machine learning models?

easy

A. To reduce the size of the training dataset

B. To remove noise from images

C. To create more varied training images by modifying originals

D. To convert images to grayscale only

Solution

1. Step 1: Understand image augmentation

   Image augmentation means making small changes to original images to create new ones.

2. Step 2: Purpose in training

   This helps models see more variety and learn better, avoiding overfitting.

3. Final Answer:

   To create more varied training images by modifying originals -> Option C

4. Quick Check:

   Image augmentation = create varied images [OK]

Hint: Augmentation means changing images to get more training data [OK]

Common Mistakes:

• Thinking augmentation reduces dataset size
• Confusing augmentation with noise removal
• Assuming augmentation only changes color

2. Which of the following is the correct way to apply a horizontal flip using PyTorch's torchvision transforms?

easy

A. transforms.RandomHorizontalFlip(p=1.0)

B. transforms.HorizontalFlip()

C. transforms.FlipHorizontal()

D. transforms.RandomFlip(direction='horizontal')

Solution

1. Step 1: Recall torchvision syntax

   PyTorch uses transforms.RandomHorizontalFlip(p=probability) to flip images horizontally.

2. Step 2: Check options

   Only transforms.RandomHorizontalFlip(p=1.0) matches the correct function and parameter style.

3. Final Answer:

   transforms.RandomHorizontalFlip(p=1.0) -> Option A

4. Quick Check:

   Correct PyTorch flip = RandomHorizontalFlip [OK]

Hint: Look for 'RandomHorizontalFlip' with probability parameter [OK]

Common Mistakes:

• Using non-existent transform names
• Missing the probability parameter
• Confusing horizontal with vertical flip

3. Given the following code snippet using torchvision transforms, what is the output image size after applying the transforms?

transform = transforms.Compose([
    transforms.Resize((128, 128)),
    transforms.RandomCrop(100),
    transforms.ToTensor()
])

image = Image.open('sample.jpg')
output = transform(image)
print(output.shape)

medium

A. [3, 128, 128]

B. [3, 100, 100]

C. [1, 100, 100]

D. [3, 228, 228]

Solution

1. Step 1: Analyze each transform step

   First, image is resized to 128x128 pixels with 3 color channels (RGB). Then a random crop of size 100x100 is taken.

2. Step 2: Determine output tensor shape

   After cropping, the image size is 100x100 with 3 channels. ToTensor() converts it to a tensor with shape [channels, height, width] = [3, 100, 100].

3. Final Answer:

   [3, 100, 100] -> Option B

4. Quick Check:

   Resize then crop = final size 100x100 [OK]

Hint: Resize then crop means output size = crop size [OK]

Common Mistakes:

• Ignoring the crop step size
• Confusing channel dimension with batch size
• Assuming crop keeps original size

4. The following code is intended to rotate an image by 45 degrees using torchvision transforms, but it raises an error. What is the mistake?

transform = transforms.Compose([
    transforms.Rotate(45),
    transforms.ToTensor()
])

image = Image.open('sample.jpg')
output = transform(image)

medium

A. transforms.Rotate doesn't exist; should use transforms.functional.rotate or transforms.RandomRotation

B. The angle 45 must be in radians, not degrees

C. ToTensor must come before Rotate

D. Image.open returns a tensor, so transform fails

Solution

1. Step 1: Check torchvision transform names

   There is no transforms.Rotate class. Rotation is done with transforms.RandomRotation or using functional API.

2. Step 2: Identify correct usage

   To rotate by a fixed angle, use transforms.RandomRotation([45, 45]) or transforms.functional.rotate. The code as is will cause an AttributeError.

3. Final Answer:

   transforms.Rotate doesn't exist; should use transforms.functional.rotate or transforms.RandomRotation -> Option A

4. Quick Check:

   No transforms.Rotate in torchvision [OK]

Hint: Check transform names carefully; Rotate is not a direct class [OK]

Common Mistakes:

• Using non-existent transform classes
• Confusing degrees and radians
• Wrong order of transforms

5. You want to augment a dataset of images to improve model robustness. Which combination of transforms would best simulate real-world variations while keeping image size constant?

hard

A. transforms.RandomCrop(224), transforms.RandomRotation(180), transforms.Resize(128)

B. transforms.Resize(256), transforms.CenterCrop(224), transforms.RandomVerticalFlip() only

C. transforms.RandomRotation(90), transforms.RandomCrop(200), transforms.ToTensor()

D. transforms.RandomResizedCrop(224), transforms.RandomHorizontalFlip(), transforms.ColorJitter(brightness=0.2, contrast=0.2)

Solution

1. Step 1: Understand augmentation goals

   We want to simulate real-world changes like size, flip, and color while keeping output size fixed.

2. Step 2: Evaluate options

   transforms.RandomResizedCrop(224), transforms.RandomHorizontalFlip(), transforms.ColorJitter(brightness=0.2, contrast=0.2) resizes and crops randomly to 224x224, flips horizontally, and changes brightness/contrast, all common augmentations that keep size constant.

3. Step 3: Check other options

   transforms.Resize(256), transforms.CenterCrop(224), transforms.RandomVerticalFlip() only flips vertically and crops but lacks color changes. transforms.RandomRotation(90), transforms.RandomCrop(200), transforms.ToTensor() changes size unpredictably and transforms.RandomCrop(224), transforms.RandomRotation(180), transforms.Resize(128) resizes after cropping, changing size.

4. Final Answer:

   transforms.RandomResizedCrop(224), transforms.RandomHorizontalFlip(), transforms.ColorJitter(brightness=0.2, contrast=0.2) -> Option D

5. Quick Check:

   Best augmentations keep size fixed and add variety [OK]

Hint: Pick transforms that keep size fixed and add flip + color changes [OK]

Common Mistakes:

• Choosing transforms that change image size unpredictably
• Ignoring color augmentations
• Using only vertical flips which are less common