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.

Practice

1. Which of the following is a common strategy to improve model performance when you have a small image dataset?

easy

A. Train a deep model from scratch without any pre-trained weights

B. Use data augmentation to create more training images

C. Ignore validation to use all data for training

D. Reduce image resolution to save memory only

Solution

1. Step 1: Understand small dataset challenges

   Small datasets often cause models to overfit and perform poorly on new data.

2. Step 2: Identify effective strategies

   Data augmentation creates new images by modifying existing ones, increasing data variety and helping the model generalize better.

3. Final Answer:

   Use data augmentation to create more training images -> Option B

4. Quick Check:

   Data augmentation = More data variety [OK]

Hint: More data variety helps small datasets [OK]

Common Mistakes:

• Training from scratch causes overfitting
• Ignoring validation hides model issues
• Reducing resolution alone doesn't add data

2. Which code snippet correctly applies data augmentation using the Python library torchvision.transforms?

easy

A. transforms.Compose([transforms.RandomHorizontalFlip(), transforms.ToTensor()])

B. transforms.RandomCrop(32, 32)

C. transforms.ToTensor(), transforms.Normalize()

D. transforms.Resize(256)

Solution

1. Step 1: Recognize data augmentation syntax

   Data augmentation requires combining multiple transforms, usually with Compose.

2. Step 2: Check which option uses Compose with augmentation

   transforms.Compose([transforms.RandomHorizontalFlip(), transforms.ToTensor()]) uses Compose with RandomHorizontalFlip (augmentation) and ToTensor (conversion), which is correct.

3. Final Answer:

   transforms.Compose([transforms.RandomHorizontalFlip(), transforms.ToTensor()]) -> Option A

4. Quick Check:

   Compose + augmentation = transforms.Compose([transforms.RandomHorizontalFlip(), transforms.ToTensor()]) [OK]

Hint: Use Compose to combine augmentations [OK]

Common Mistakes:

• Using single transform without Compose
• Missing ToTensor conversion
• Using only resizing without augmentation

3. Consider this Python code using transfer learning with PyTorch:

import torchvision.models as models
model = models.resnet18(pretrained=True)
for param in model.parameters():
    param.requires_grad = False
model.fc = torch.nn.Linear(512, 2)

What does this code do?

medium

A. Trains all layers of ResNet18 from scratch

B. Unfreezes all layers for fine-tuning

C. Freezes all layers except the last fully connected layer

D. Removes the last layer without replacement

Solution

1. Step 1: Analyze parameter freezing

   The loop sets requires_grad=False for all parameters, freezing them during training.

2. Step 2: Check the last layer replacement

   The last fully connected layer (fc) is replaced with a new Linear layer, which by default has requires_grad=True.

3. Final Answer:

   Freezes all layers except the last fully connected layer -> Option C

4. Quick Check:

   Freeze all but last layer = Freezes all layers except the last fully connected layer [OK]

Hint: Freeze parameters, then replace last layer [OK]

Common Mistakes:

• Assuming all layers are trainable
• Not noticing last layer replacement
• Confusing freezing with unfreezing

4. You wrote this code to augment images but get an error:

transform = transforms.Compose([
    transforms.RandomRotation(30),
    transforms.ToTensor
])

What is the error and how to fix it?

medium

A. Transforms must be applied outside Compose

B. RandomRotation requires degrees as a tuple, fix by using (0,30)

C. Compose should be replaced by Sequential

D. Missing parentheses after ToTensor; fix by using transforms.ToTensor()

Solution

1. Step 1: Identify the error in ToTensor usage

   transforms.ToTensor is a class, missing parentheses means it's not called, causing an error.

2. Step 2: Correct the syntax

   Add parentheses to call ToTensor: transforms.ToTensor()

3. Final Answer:

   Missing parentheses after ToTensor; fix by using transforms.ToTensor() -> Option D

4. Quick Check:

   Call ToTensor() as function [OK]

Hint: Call transform classes with () [OK]

Common Mistakes:

• Forgetting parentheses on transform classes
• Misusing Compose with wrong functions
• Incorrect argument types for RandomRotation

5. You have only 100 labeled images for a classification task. Which combined approach best improves model accuracy?

hard

A. Use transfer learning with a pre-trained model and apply data augmentation

B. Train a deep CNN from scratch with no augmentation

C. Use only data augmentation without pre-trained weights

D. Increase batch size to 512 and train for fewer epochs

Solution

1. Step 1: Understand small dataset limits

   With only 100 images, training deep models from scratch risks overfitting and poor generalization.

2. Step 2: Combine transfer learning and augmentation

   Transfer learning uses knowledge from large datasets, and augmentation increases data variety, both improving accuracy.

3. Final Answer:

   Use transfer learning with a pre-trained model and apply data augmentation -> Option A

4. Quick Check:

   Transfer learning + augmentation = Best for small data [OK]

Hint: Combine pre-trained models with augmentation [OK]

Common Mistakes:

• Training from scratch with little data
• Relying on augmentation alone
• Using too large batch size causing poor learning