Small dataset strategies in Computer Vision

Introduction

Sometimes, you have only a few images to teach a computer to see. Small dataset strategies help you get good results even with little data.

You want to build a model but have only a few pictures.

Collecting more images is expensive or slow.

You want to quickly test ideas without waiting for big data.

You want to improve accuracy when data is limited.

You want to avoid overfitting on small image sets.

Syntax

Computer Vision

1. Use data augmentation to create new images from old ones.
2. Use transfer learning with a pre-trained model.
3. Use few-shot learning techniques.
4. Use synthetic data generation.
5. Use regularization to avoid overfitting.

These are general steps, not code lines.

Each step can be done with different tools and libraries.

Examples

This example shows how to create new images by rotating and flipping existing ones.

Computer Vision

from tensorflow.keras.preprocessing.image import ImageDataGenerator

datagen = ImageDataGenerator(
    rotation_range=20,
    width_shift_range=0.1,
    height_shift_range=0.1,
    horizontal_flip=True
)

# Use datagen.flow() to generate augmented images

This example shows how to use a pre-trained model to help learn from few images.

Computer Vision

from tensorflow.keras.applications import MobileNetV2

base_model = MobileNetV2(weights='imagenet', include_top=False)
# Use base_model as feature extractor for your small dataset

Sample Model

This program shows how to use data augmentation and transfer learning together to train a model on a small image dataset.

Computer Vision

import tensorflow as tf
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.applications import MobileNetV2
from tensorflow.keras import layers, models

# Create data augmentation generator
train_datagen = ImageDataGenerator(
    rotation_range=20,
    width_shift_range=0.1,
    height_shift_range=0.1,
    horizontal_flip=True,
    rescale=1./255
)

# Assume images are in 'train/' folder with subfolders for classes
train_generator = train_datagen.flow_from_directory(
    'train/',
    target_size=(128, 128),
    batch_size=16,
    class_mode='binary'
)

# Load pre-trained MobileNetV2 without top layers
base_model = MobileNetV2(weights='imagenet', include_top=False, input_shape=(128, 128, 3))
base_model.trainable = False  # Freeze base model

# Add new classification layers
model = models.Sequential([
    base_model,
    layers.GlobalAveragePooling2D(),
    layers.Dense(1, activation='sigmoid')
])

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

# Train model on small dataset with augmentation
model.fit(train_generator, epochs=3)

print('Training complete')

Important Notes

Data augmentation helps create variety from few images.

Transfer learning uses knowledge from big datasets to help small ones.

Freezing the base model avoids losing pre-trained knowledge.

Summary

Small dataset strategies help computers learn from few images.

Use data augmentation and transfer learning to improve results.

These methods reduce overfitting and improve accuracy.

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