Data augmentation importance in Computer Vision - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is data augmentation in computer vision?

Data augmentation is a technique that creates new training images by modifying existing ones, like flipping, rotating, or changing colors, to help the model learn better.

beginner

Why is data augmentation important for training computer vision models?

It helps the model see more varied examples, which reduces overfitting and improves its ability to recognize objects in new, unseen images.

intermediate

How does data augmentation help with overfitting?

By increasing the diversity of training images, data augmentation prevents the model from memorizing exact images and encourages it to learn general patterns.

beginner

Name three common data augmentation techniques used in computer vision.

Common techniques include flipping images horizontally, rotating images by small angles, and adjusting brightness or contrast.

intermediate

Can data augmentation replace collecting more real data? Why or why not?

No, data augmentation helps but cannot fully replace real data because it only modifies existing images and may not capture all real-world variations.

What is the main goal of data augmentation in computer vision?

A Increase training data variety to improve model learning

B Reduce the size of the training dataset

C Make images look more colorful

D Remove noise from images

Data augmentation increases the variety of training data to help the model learn better and generalize well.

Which of the following is NOT a common data augmentation technique?

A Horizontal flipping

B Deleting pixels permanently

C Image rotation

D Adding random noise

Deleting pixels permanently is not a standard augmentation technique because it can remove important image information.

How does data augmentation affect overfitting?

A It increases overfitting

B It causes the model to memorize data

C It has no effect

D It reduces overfitting by adding variety

Data augmentation reduces overfitting by providing more varied examples for the model to learn from.

Why can't data augmentation fully replace collecting new real images?

A Because it only modifies existing images and may miss real-world variations

B Because augmented images are always blurry

C Because it is too slow

D Because it requires special hardware

Data augmentation modifies existing images but cannot create completely new real-world scenarios.

Which of these is a benefit of using data augmentation?

A Less memory usage

B Faster training time

C Improved model generalization

D Simpler model architecture

Data augmentation helps the model generalize better by exposing it to more varied data.

Explain why data augmentation is important for training computer vision models.

Think about how seeing more different images helps a model perform better on new images.

List and describe three common data augmentation techniques used in computer vision.

Consider simple ways to change images without changing their meaning.

Practice

1. Why is data augmentation important in training computer vision models?

easy

A. It increases the variety of training images to help the model generalize better.

B. It reduces the size of the training dataset to speed up training.

C. It removes noisy images from the dataset automatically.

D. It guarantees 100% accuracy on the training data.

Solution

1. Step 1: Understand data augmentation purpose

   Data augmentation creates new images by slightly changing existing ones to increase variety.

2. Step 2: Connect augmentation to model learning

   More variety helps the model learn features that work on new, unseen images, improving generalization.

3. Final Answer:

   It increases the variety of training images to help the model generalize better. -> Option A

4. Quick Check:

   Data augmentation = better generalization [OK]

Hint: Think: more image variety means better learning [OK]

Common Mistakes:

• Confusing augmentation with data reduction
• Believing augmentation removes bad images
• Assuming augmentation guarantees perfect accuracy

2. Which of the following is a correct way to apply horizontal flip augmentation using Python's torchvision library?

easy

A. transforms.FlipHorizontal(prob=0.5)

B. transforms.HorizontalFlip(0.5)

C. transforms.RandomHorizontalFlip(p=0.5)

D. transforms.RandomFlipHorizontal()

Solution

1. Step 1: Recall torchvision syntax for horizontal flip

   The correct transform is RandomHorizontalFlip with a probability parameter p.

2. Step 2: Check each option's correctness

   Only transforms.RandomHorizontalFlip(p=0.5) matches the correct syntax and parameter name.

3. Final Answer:

   transforms.RandomHorizontalFlip(p=0.5) -> Option C

4. Quick Check:

   Correct torchvision flip syntax = transforms.RandomHorizontalFlip(p=0.5) [OK]

Hint: Look for 'RandomHorizontalFlip' with parameter p= [OK]

Common Mistakes:

• Using wrong class names like HorizontalFlip
• Incorrect parameter names like prob instead of p
• Missing the probability parameter

3. What will be the output shape of the augmented image after applying the following PyTorch transform?

transform = transforms.Compose([
  transforms.Resize((128, 128)),
  transforms.RandomRotation(30),
  transforms.ToTensor()
])
augmented_image = transform(original_image)

medium

A. [128, 3, 128]

B. [128, 128, 3]

C. [1, 128, 128]

D. [3, 128, 128]

Solution

1. Step 1: Analyze the transform steps

   Resize changes image to 128x128 pixels. RandomRotation keeps size same. ToTensor converts image to tensor with channels first.

2. Step 2: Determine tensor shape format

   PyTorch tensors from images have shape [channels, height, width]. For RGB images, channels=3.

3. Final Answer:

   [3, 128, 128] -> Option D

4. Quick Check:

   PyTorch image tensor shape = [channels, height, width] [OK]

Hint: PyTorch image tensors are channels first: [3, H, W] [OK]

Common Mistakes:

• Confusing channel order with height and width
• Assuming rotation changes image size
• Mixing up tensor shape formats

4. You wrote this augmentation code but get an error:

transform = transforms.Compose([
  transforms.RandomRotation(45),
  transforms.RandomHorizontalFlip(0.3),
  transforms.ToTensor()
])

What is the likely cause?

medium

A. RandomHorizontalFlip expects a keyword argument p, not a positional float.

B. RandomRotation requires integer degrees, not float.

C. ToTensor must come before RandomRotation.

D. Compose cannot combine these transforms.

Solution

1. Step 1: Check RandomHorizontalFlip usage

   RandomHorizontalFlip requires the probability parameter as a keyword argument p=, not a positional argument.

2. Step 2: Verify other transform usages

   RandomRotation accepts float degrees, ToTensor can be last, Compose supports these transforms.

3. Final Answer:

   RandomHorizontalFlip expects a keyword argument p, not a positional float. -> Option A

4. Quick Check:

   RandomHorizontalFlip(p=0.3) correct syntax [OK]

Hint: Check if transform params use correct keywords [OK]

Common Mistakes:

• Passing probability as positional argument
• Thinking rotation degrees must be integer
• Misordering transforms in Compose

5. You have a small dataset of 100 images for a classification task. Which data augmentation strategy will most likely improve your model's ability to recognize objects in new photos?

hard

A. Only resize images to a fixed size without any other changes.

B. Apply random flips, rotations up to 30 degrees, and brightness changes during training.

C. Add Gaussian noise to all images without any geometric transforms.

D. Train without augmentation but increase model layers.

Solution

1. Step 1: Consider dataset size and augmentation needs

   Small datasets benefit from augmentations that create varied views of images to prevent overfitting.

2. Step 2: Evaluate augmentation types

   Random flips, rotations, and brightness changes simulate real-world variations, improving generalization better than noise alone or no augmentation.

3. Final Answer:

   Apply random flips, rotations up to 30 degrees, and brightness changes during training. -> Option B

4. Quick Check:

   Varied augmentations = better generalization on small data [OK]

Hint: Use varied simple transforms for small datasets [OK]

Common Mistakes:

• Ignoring augmentation on small datasets
• Using only noise without geometric changes
• Relying on bigger models instead of data variety