Small dataset strategies in Computer Vision - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is data augmentation in the context of small datasets?

Data augmentation means creating new images by changing existing ones slightly, like flipping or rotating. This helps the model learn better from limited data.

beginner

Why is transfer learning useful for small datasets?

Transfer learning uses a model trained on a big dataset and adapts it to a small dataset. It saves time and improves accuracy when data is limited.

intermediate

How does cross-validation help with small datasets?

Cross-validation splits data into parts to train and test multiple times. This gives a better idea of how well the model works on unseen data.

intermediate

What is the role of pre-trained models in small dataset strategies?

Pre-trained models have learned features from large datasets. Using them helps when you have few images, as they already know useful patterns.

beginner

Name one challenge of working with small datasets in computer vision.

One challenge is overfitting, where the model learns the training images too well but fails to generalize to new images.

Which technique creates new images by flipping or rotating existing ones?

A Transfer learning

B Cross-validation

C Data augmentation

D Feature extraction

Data augmentation involves modifying images to increase dataset size.

What does transfer learning use to improve model training on small datasets?

A Pre-trained models

B Random noise

C New labels

D Data splitting

Transfer learning uses pre-trained models to leverage prior knowledge.

Why is cross-validation important for small datasets?

A It increases dataset size

B It helps estimate model performance reliably

C It reduces image resolution

D It removes noisy images

Cross-validation tests the model multiple times to check performance.

What problem occurs when a model learns training data too well but fails on new data?

A Normalization

B Underfitting

C Data leakage

D Overfitting

Overfitting means the model memorizes training data and does not generalize.

Which of these is NOT a common small dataset strategy?

A Increasing image size

B Transfer learning

C Cross-validation

D Data augmentation

Increasing image size does not help with small dataset problems.

Explain three strategies to improve model performance when you have a small image dataset.

Think about ways to create more data, reuse existing knowledge, and test model reliability.

Describe why overfitting is a concern with small datasets and how to reduce it.

Consider what happens when the model sees too few examples.