Dataset bias in vision in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding Dataset Bias in Vision Models

Which of the following best describes dataset bias in computer vision?

A When the training data does not represent the real-world diversity, causing the model to perform poorly on unseen data.

B When the model architecture is too simple to learn complex patterns in images.

C When the dataset contains corrupted or missing image files.

D When the model is trained for too many epochs causing overfitting.

💡 Hint

Think about how the data used to train the model affects its ability to generalize.

Dataset bias occurs when the training data lacks diversity or is skewed, so the model learns patterns that do not generalize well to new, different data.

❓ data_output

intermediate

Detecting Bias in Image Dataset Distribution

You have a dataset with images labeled as 'cat' or 'dog'. The dataset has 900 cat images and 100 dog images. What is the class distribution ratio?

Computer Vision

labels = ['cat'] * 900 + ['dog'] * 100
from collections import Counter
class_counts = Counter(labels)
ratio = class_counts['cat'] / class_counts['dog']
print(ratio)

A 9.0

B 0.11

C 1.0

D 10.0

💡 Hint

Divide the number of cat images by the number of dog images.

There are 900 cat images and 100 dog images, so the ratio is 900/100 = 9.0.

❓ visualization

advanced

Visualizing Dataset Bias with Image Counts

Given a dataset with image counts per class, which bar chart correctly shows the bias towards one class?

Computer Vision

import matplotlib.pyplot as plt
classes = ['cat', 'dog', 'rabbit']
counts = [900, 100, 50]
plt.bar(classes, counts, color=['blue', 'orange', 'green'])
plt.title('Image Counts per Class')
plt.xlabel('Class')
plt.ylabel('Number of Images')
plt.show()

A A line chart showing counts over time.

B A bar chart with all bars equal height.

C A bar chart with 'rabbit' bar tallest, 'dog' medium, 'cat' shortest.

D A bar chart with 'cat' bar much taller than 'dog' and 'rabbit' bars.

💡 Hint

Look for the chart where one class has many more images than others.

The dataset has 900 cat images, which is much more than dog (100) and rabbit (50), so the cat bar should be tallest.

🔧 Debug

advanced

Identifying Bias Impact in Model Accuracy

Consider a model trained on a biased dataset with mostly cats. The accuracy on cats is 95%, but on dogs is 60%. What is the likely cause?

A The model architecture is too complex causing overfitting on cats.

B The training was stopped too early before learning dog features.

C The model learned mostly from cat images and struggles to generalize to dogs due to dataset bias.

D The dog images are corrupted causing low accuracy.

💡 Hint

Think about how the imbalance in training data affects model performance on different classes.

Because the dataset has many more cat images, the model learns cat features well but poorly learns dog features, causing lower accuracy on dogs.

🚀 Application

expert

Mitigating Dataset Bias in Vision Models

You have a dataset with strong bias: 90% of images are indoor scenes, 10% outdoor. You want to train a model that works well on both. Which approach is best?

A Ignore the bias and train on the full dataset as is.

B Use data augmentation to increase outdoor images and balance the dataset before training.

C Train only on indoor images since they are the majority to maximize accuracy.

D Remove all indoor images and train only on outdoor images.

💡 Hint

Think about how to balance the dataset to reduce bias.

Data augmentation can increase the number of outdoor images, balancing the dataset and helping the model learn features from both indoor and outdoor scenes.