Data augmentation importance in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Why use data augmentation in training image models?

Imagine you have a small set of photos to teach a computer to recognize cats. Why is it helpful to use data augmentation?

A It converts images to grayscale to simplify the model.

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

C It removes noisy images from the dataset to improve accuracy.

D It creates new images by changing existing ones, helping the model learn more varied examples.

💡 Hint

Think about how changing images slightly can help the model see more types of cats.

Data augmentation creates new training images by applying transformations like rotation or flipping. This helps the model learn to recognize objects in different conditions, improving its ability to generalize.

❓ Predict Output

intermediate

Output of augmented image shape

Given this code snippet using TensorFlow's image augmentation, what is the shape of the output image?

Computer Vision

import tensorflow as tf

image = tf.random.uniform(shape=(100, 100, 3))
augmented = tf.image.random_flip_left_right(image)
print(augmented.shape)

A (100, 100, 3)

B (100, 100)

C (3, 100, 100)

D (None, None, 3)

💡 Hint

Flipping an image horizontally does not change its shape.

The random_flip_left_right function flips the image horizontally but keeps the original shape (height, width, channels).

❓ Model Choice

advanced

Choosing a model to test data augmentation effect

You want to test how data augmentation improves model performance on a small image dataset. Which model choice is best to clearly see the effect?

A A random forest model on raw pixel values.

B A simple CNN with few layers trained with and without augmentation.

C A very deep CNN pretrained on a large dataset without augmentation.

D A linear regression model on flattened images.

💡 Hint

Think about a model that can learn from images and show clear differences when data changes.

A simple CNN trained from scratch on a small dataset will benefit noticeably from augmentation, showing clearer performance differences.

❓ Hyperparameter

advanced

Best augmentation intensity for small datasets

When applying data augmentation to a small image dataset, which approach to augmentation intensity usually helps the model most?

A Use no augmentation to keep original data quality.

B Use very strong augmentation to create completely new images.

C Use moderate augmentation to increase diversity without making images unrealistic.

D Use only color changes without geometric transformations.

💡 Hint

Think about balancing new examples and keeping images recognizable.

Moderate augmentation helps the model see varied but realistic images, improving generalization without confusing it with unrealistic data.

❓ Metrics

expert

Evaluating augmentation impact on model metrics

You trained two image classifiers: one with data augmentation and one without. After training, the augmented model has higher training loss but better validation accuracy. What does this indicate?

A Augmentation helps reduce overfitting by making training harder but improving generalization.

B Augmentation causes the model to underfit, so it performs worse overall.

C Higher training loss means the augmented model is worse in every way.

D Validation accuracy is unreliable; only training loss matters.

💡 Hint

Think about what it means when training is harder but validation improves.

Data augmentation makes training data more varied and challenging, increasing training loss but helping the model generalize better, shown by improved validation accuracy.

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