Why augmentation multiplies training data in Computer Vision

Introduction

Augmentation creates new versions of images by changing them slightly. This helps the model learn better by seeing more varied examples without needing more real pictures.

When you have a small number of images but want to train a strong model.

When you want your model to recognize objects from different angles or lighting.

When you want to reduce overfitting by making the training data more diverse.

When collecting new images is expensive or time-consuming.

When you want to improve model performance on real-world variations.

Syntax

Computer Vision

augmented_image = augmentation_function(original_image)

# Example augmentations:
# rotated_image = rotate(original_image, angle)
# flipped_image = flip(original_image, direction)
# bright_image = change_brightness(original_image, factor)

Augmentation functions take an image and return a changed version of it.

You can apply multiple augmentations to create many new images.

Examples

Rotate the image by 15 degrees to create a new training example.

Computer Vision

rotated_image = rotate(original_image, 15)

Flip the image horizontally to simulate a mirror image.

Computer Vision

flipped_image = flip(original_image, 'horizontal')

Increase brightness by 20% to simulate different lighting.

Computer Vision

bright_image = change_brightness(original_image, 1.2)

Create four rotated versions of the image at different angles.

Computer Vision

augmented_images = [rotate(img, angle) for angle in [0, 90, 180, 270]]

Sample Model

This code creates one simple image and makes two new images by rotating and flipping it. It shows how augmentation multiplies the training data.

Computer Vision

import numpy as np
import cv2

# Create a simple black square image
original_image = np.zeros((100, 100, 3), dtype=np.uint8)
cv2.rectangle(original_image, (30, 30), (70, 70), (255, 255, 255), -1)

# Define augmentation functions
def rotate(image, angle):
    center = (image.shape[1] // 2, image.shape[0] // 2)
    matrix = cv2.getRotationMatrix2D(center, angle, 1.0)
    rotated = cv2.warpAffine(image, matrix, (image.shape[1], image.shape[0]))
    return rotated

def flip(image, direction):
    if direction == 'horizontal':
        return cv2.flip(image, 1)
    elif direction == 'vertical':
        return cv2.flip(image, 0)
    else:
        return image

# Apply augmentations
rotated_90 = rotate(original_image, 90)
flipped_h = flip(original_image, 'horizontal')

# Count total images
original_count = 1
augmented_count = 2

print(f"Original images: {original_count}")
print(f"Augmented images: {augmented_count}")
print(f"Total training images: {original_count + augmented_count}")

Important Notes

Augmentation does not create new real data but new views of existing data.

Too much augmentation can confuse the model if changes are unrealistic.

Common augmentations include rotation, flipping, scaling, and color changes.

Summary

Augmentation helps models learn better by showing more varied images.

It multiplies training data by creating new versions of existing images.

This technique is useful when real data is limited or costly to get.

Practice

1. Why does image augmentation multiply the training data in computer vision?

easy

A. Because it creates new images by changing existing ones

B. Because it deletes some images to reduce overfitting

C. Because it compresses images to save space

D. Because it labels images automatically

Solution

1. Step 1: Understand augmentation purpose

   Augmentation creates new images by applying changes like rotation or flipping to existing images.

2. Step 2: Connect augmentation to data size

   These new images increase the total number of training samples, effectively multiplying the dataset size.

3. Final Answer:

   Because it creates new images by changing existing ones -> Option A

4. Quick Check:

   Augmentation = new image versions [OK]

Hint: Augmentation makes new images from old ones [OK]

Common Mistakes:

• Thinking augmentation deletes images
• Confusing augmentation with compression
• Believing augmentation automatically labels data

2. Which of the following Python code snippets correctly applies horizontal flip augmentation using torchvision transforms?

easy

A. transform = transforms.FlipHorizontal()

B. transform = transforms.HorizontalFlip()

C. transform = transforms.RandomHorizontalFlip(p=1.0)

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

Solution

1. Step 1: Recall torchvision syntax

   In torchvision, horizontal flip is done with RandomHorizontalFlip and a probability parameter.

2. Step 2: Check options for correct class and parameters

   Only transform = transforms.RandomHorizontalFlip(p=1.0) uses the correct class name and parameter format.

3. Final Answer:

   transform = transforms.RandomHorizontalFlip(p=1.0) -> Option C

4. Quick Check:

   Correct torchvision flip syntax = transform = transforms.RandomHorizontalFlip(p=1.0) [OK]

Hint: Look for RandomHorizontalFlip with p parameter [OK]

Common Mistakes:

• Using incorrect class names like HorizontalFlip
• Missing the probability parameter p
• Assuming FlipHorizontal exists in torchvision

3. Given this code snippet applying augmentation, what is the total number of images after augmentation if the original dataset has 100 images and each image is augmented with 3 different transformations?

medium

A. 300

B. 400

C. 100

D. 600

Solution

1. Step 1: Calculate augmented images per original

   Each original image produces 3 new augmented images plus the original itself, totaling 4 images per original.

2. Step 2: Multiply by original dataset size

   100 original images * 4 images each = 400 images total after augmentation.

3. Final Answer:

   400 -> Option B

4. Quick Check:

   (3 augmentations + 1 original) * 100 = 400 [OK]

Hint: Add original + augmentations, then multiply by dataset size [OK]

Common Mistakes:

• Counting only augmented images, ignoring originals
• Multiplying by 3 instead of 4
• Adding instead of multiplying

4. Identify the error in this augmentation code snippet and select the fix:

from torchvision import transforms
transform = transforms.Compose([
    transforms.RandomRotation(30),
    transforms.RandomFlip(horizontal=true)
])

medium

A. Replace RandomFlip with RandomHorizontalFlip

B. Change RandomRotation(30) to RandomRotation(degrees=30)

C. Add p=0.5 to RandomFlip

D. No error, code is correct

Solution

1. Step 1: Check torchvision augmentation classes

   There is no RandomFlip class in torchvision; horizontal flip uses RandomHorizontalFlip.

2. Step 2: Identify correct fix

   Replacing RandomFlip with RandomHorizontalFlip fixes the error; other options are incorrect or unnecessary.

3. Final Answer:

   Replace RandomFlip with RandomHorizontalFlip -> Option A

4. Quick Check:

   Correct flip class = RandomHorizontalFlip [OK]

Hint: Use exact torchvision class names for flips [OK]

Common Mistakes:

• Assuming RandomFlip exists
• Changing rotation syntax unnecessarily
• Adding parameters to non-existent classes

5. You have a small dataset of 50 images. You want to multiply your training data by 5 times using augmentation. Which combination of augmentations is best to achieve this without losing original images?

hard

A. Apply 5 augmentations but discard original images

B. Only keep original images and train longer

C. Apply 2 augmentations and duplicate images twice

D. Apply 4 different augmentations per image plus keep original images

Solution

1. Step 1: Understand multiplication goal

   To multiply data by 5 times, total images after augmentation should be 50 * 5 = 250.

2. Step 2: Calculate images per original

   Keeping original plus 4 augmentations per image gives 5 images per original, totaling 250 images.

3. Step 3: Evaluate options

   Apply 4 different augmentations per image plus keep original images achieves the goal without losing original images; others either discard originals or don't reach 5x.

4. Final Answer:

   Apply 4 different augmentations per image plus keep original images -> Option D

5. Quick Check:

   Original + 4 augmentations = 5x data [OK]

Hint: Keep originals + 4 augmentations for 5x data [OK]

Common Mistakes:

• Discarding original images reduces data size
• Duplicating images without augmentation doesn't add variety
• Training longer without augmentation doesn't multiply data