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.

Practice

1. What does dataset bias in computer vision mean?

easy

A. The data does not fairly represent all types of images or cases

B. The model always predicts perfectly on all images

C. The dataset is too large to process

D. The images are all black and white

Solution

1. Step 1: Understand dataset bias meaning

   Dataset bias means the data used to train a model does not cover all possible cases fairly.

2. Step 2: Compare options to definition

   Only The data does not fairly represent all types of images or cases describes this correctly. Other options describe unrelated issues.

3. Final Answer:

   The data does not fairly represent all types of images or cases -> Option A

4. Quick Check:

   Dataset bias = unfair data representation [OK]

Hint: Bias means data is not fair or balanced [OK]

Common Mistakes:

• Thinking bias means model is perfect
• Confusing bias with dataset size
• Assuming bias means image color

2. Which of the following is the correct way to check for dataset bias in a vision dataset using Python?

easy

A. Use random.shuffle(dataset) to fix bias

B. Use value_counts() on labels to see class distribution

C. Use len(dataset) without checking labels

D. Use print(dataset) only

Solution

1. Step 1: Identify method to check bias

   Checking class distribution with value_counts() helps find imbalance in labels.

2. Step 2: Evaluate other options

   Printing dataset or length alone doesn't show bias. Shuffling data doesn't check bias.

3. Final Answer:

   Use value_counts() on labels to see class distribution -> Option B

4. Quick Check:

   Check label counts = value_counts() [OK]

Hint: Check label counts to find bias [OK]

Common Mistakes:

• Only printing dataset without analysis
• Assuming dataset length shows bias
• Thinking shuffling fixes bias

3. Given this Python code snippet analyzing a vision dataset labels:

import pandas as pd
labels = ['cat', 'dog', 'cat', 'cat', 'dog', 'bird']
label_counts = pd.Series(labels).value_counts()
print(label_counts)

What is the output?

medium

A. bird 3
cat 2
dog 1

B. cat 2
dog 3
bird 1

C. cat 3
dog 2
bird 1

D. dog 3
cat 3
bird 3

Solution

1. Step 1: Count occurrences of each label

   Labels list has 'cat' 3 times, 'dog' 2 times, and 'bird' 1 time.

2. Step 2: Understand value_counts output

   value_counts() returns counts sorted descending by default.

3. Final Answer:

   cat 3\ndog 2\nbird 1 -> Option C

4. Quick Check:

   Count labels correctly = cat:3, dog:2, bird:1 [OK]

Hint: Count each label frequency carefully [OK]

Common Mistakes:

• Mixing counts of dog and cat
• Assuming alphabetical order instead of count order
• Miscounting occurrences

4. You have this code to check dataset bias:

labels = ['car', 'car', 'truck', 'car', 'truck']
counts = {}
for label in labels:
    counts[label] = counts.get(label, 0) + 1
print(counts)

But the output is {}. What is the likely error?

medium

A. The 'get' method is used incorrectly with wrong parameters

B. The print statement is outside the loop and missing indentation

C. The code is correct; output should be {'car': 3, 'truck': 2}

D. The dictionary 'counts' was reinitialized inside the loop

Solution

1. Step 1: Analyze code behavior

   If 'counts' is reset inside the loop, it will be empty after loop ends.

2. Step 2: Identify cause of empty output

   Reinitializing 'counts' inside loop clears previous counts, causing empty dict at print.

3. Final Answer:

   The dictionary 'counts' was reinitialized inside the loop -> Option D

4. Quick Check:

   Resetting dict inside loop empties counts [OK]

Hint: Check if dict is reset inside loop [OK]

Common Mistakes:

• Thinking print indentation causes empty output
• Assuming get() method is wrong
• Ignoring variable scope inside loop

5. You have a vision dataset with 90% images of cats and 10% dogs. Which method best reduces dataset bias to improve model fairness?

hard

A. Collect more dog images to balance classes

B. Remove all cat images to keep only dogs

C. Train model only on cat images

D. Ignore class imbalance and train as is

Solution

1. Step 1: Understand dataset imbalance problem

   Having 90% cats and 10% dogs causes bias favoring cats.

2. Step 2: Choose method to fix bias

   Collecting more dog images balances classes, reducing bias and improving fairness.

3. Final Answer:

   Collect more dog images to balance classes -> Option A

4. Quick Check:

   Balance classes by adding data [OK]

Hint: Balance classes by adding underrepresented data [OK]

Common Mistakes:

• Removing majority class loses useful data
• Training on one class ignores others
• Ignoring imbalance causes biased model