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.