Why augmentation multiplies training data in Computer Vision - Challenge Your Understanding

Challenge - 5 Problems

🧠 Conceptual

intermediate

Why does data augmentation increase training data size?

Imagine you have 100 pictures of cats. You flip each picture horizontally to create new images. How does this affect the number of training images?

A It halves the number of images because flipping removes some images.

B It keeps the number of images the same because flipped images are not counted separately.

C It doubles the number of training images because each original image creates one new flipped image.

D It triples the number of images because flipping creates two new images per original.

💡 Hint

Think about how many images you have before and after flipping.

Each original image creates one new image by flipping, so total images become original + flipped = 2 times original.

🧠 Conceptual

intermediate

How does rotation augmentation affect training data?

If you rotate each image in your dataset by 90, 180, and 270 degrees, how many images will you have compared to the original?

A Four times the original number because each image creates three rotated versions plus the original.

B Three times the original number because only three rotations are added.

C The same number because rotations do not add new images.

D Twice the original number because only one rotation is used.

💡 Hint

Count the original plus all rotated versions.

Each image generates three new rotated images plus the original, so total images are 4 times the original.

❓ Predict Output

advanced

Output of augmented dataset size calculation

What is the output of this code that calculates augmented dataset size?

Computer Vision

original_size = 150
augmentations_per_image = 5
augmented_size = original_size * (augmentations_per_image + 1)
print(augmented_size)

A 150

B 900

C 155

D 750

💡 Hint

Remember to add the original images to the augmented ones.

The total dataset size is original images plus 5 augmentations each, so 150 * (5 + 1) = 900.

❓ Metrics

advanced

Effect of augmentation on training accuracy

Which statement best explains why data augmentation can improve training accuracy?

A Augmentation increases data variety, helping the model learn better and generalize well.

B Augmentation reduces the number of training samples, making training faster.

C Augmentation removes noisy data, improving accuracy.

D Augmentation duplicates data without changes, which does not affect accuracy.

💡 Hint

Think about how variety in data affects learning.

Augmentation creates diverse examples, helping the model avoid overfitting and improve accuracy.

🔧 Debug

expert

Why does this augmentation code produce fewer images than expected?

Given this code snippet, why does the augmented dataset have fewer images than expected?

Computer Vision

images = [img1, img2, img3]
augmented_images = []
for img in images:
    augmented_images.append(img)
    augmented_images.append(flip(img))
    augmented_images.append(rotate(img))
print(len(augmented_images))

A The augmented_images list is cleared inside the loop.

B The flip function modifies images in place, so duplicates are not added.

C The loop skips the last image, reducing total images.

D The rotate function returns None, so fewer images are added.

💡 Hint

Check what the rotate function returns.

If rotate returns None, appending it adds None instead of an image, so the count of valid images is less.