Small dataset strategies in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Why use data augmentation with small image datasets?

Imagine you have only 100 images to train a computer vision model. Why is data augmentation helpful in this case?

A It removes noisy images to improve dataset quality.

B It artificially increases the dataset size by creating modified versions of images, helping the model learn better.

C It compresses images to reduce storage space.

D It converts images to grayscale to simplify the model.

💡 Hint

Think about how to get more training examples without collecting new images.

Data augmentation creates new images by rotating, flipping, or changing brightness. This helps the model see more variety and learn better from limited data.

❓ Predict Output

intermediate

Output of image flipping augmentation code

What will be the shape of the output image after applying horizontal flip augmentation using this code?

Computer Vision

import numpy as np
image = np.random.rand(64, 64, 3)
flipped_image = np.flip(image, axis=1)
print(flipped_image.shape)

A (64, 64, 3)

B (3, 64, 64)

C (64, 3, 64)

D (128, 64, 3)

💡 Hint

Flipping changes pixel order but not image dimensions.

The flip operation reverses pixels along the width (axis=1) but keeps the shape the same.

❓ data_output

advanced

Resulting dataset size after augmentation

You have 50 images. You apply 3 augmentation techniques: rotation, horizontal flip, and brightness change. Each technique creates one new image per original image. How many images will you have after augmentation?

A 100

B 150

C 200

D 250

💡 Hint

Count original images plus all augmented images.

Each of the 3 augmentations creates 50 new images, so total images = 50 original + 3*50 = 200.

🔧 Debug

advanced

Identify the error in transfer learning code snippet

What error will this code produce when trying to fine-tune a pretrained model on a small dataset?

Computer Vision

from tensorflow.keras.applications import MobileNetV2
from tensorflow.keras.layers import Dense, GlobalAveragePooling2D
from tensorflow.keras.models import Model

base_model = MobileNetV2(weights='imagenet', include_top=False, input_shape=(224,224,3))
for layer in base_model.layers:
    layer.trainable = False
x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(10, activation='softmax')(x)
model = Model(inputs=base_model.input, outputs=x)
model.compile(optimizer='adam', loss='categorical_crossentropy')

A SyntaxError from missing colon in for loop

B TypeError because base_model has no attribute 'output'

C No error, code runs fine

D ValueError due to Dense layer applied to 4D tensor without flattening

💡 Hint

Check the shape of the output from base_model before Dense layer.

The base_model output is a 4D tensor (batch, height, width, channels). Dense layers expect 2D input, so flattening or global pooling is needed before Dense.

🚀 Application

expert

Best strategy to improve model accuracy on very small image dataset

You have only 30 labeled images for a classification task. You want to improve your model's accuracy. Which strategy is most effective?

A Use transfer learning with a pretrained model and freeze most layers, then fine-tune on your data.

B Train a deep neural network from scratch with many layers and epochs.

C Use only the original images without augmentation to avoid noise.

D Reduce image resolution drastically to speed up training.

💡 Hint

Think about leveraging existing knowledge from large datasets.

Transfer learning uses knowledge from large datasets to help learning on small datasets. Freezing most layers prevents overfitting and fine-tuning adapts the model to your data.