Segmentation evaluation (IoU, Dice) in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Calculate IoU for two binary masks

Given two binary masks representing segmentation results, what is the output of the following code calculating the Intersection over Union (IoU)?

Computer Vision

import numpy as np
mask1 = np.array([[1, 0, 1], [0, 1, 0], [1, 0, 0]])
mask2 = np.array([[1, 1, 0], [0, 1, 0], [1, 0, 1]])
intersection = np.logical_and(mask1, mask2).sum()
union = np.logical_or(mask1, mask2).sum()
iou = intersection / union
print(round(iou, 2))

A 0.43

B 0.50

C 0.57

D 0.67

💡 Hint

Count how many pixels overlap and how many pixels are in either mask.

IoU is the ratio of overlapping pixels (intersection) to total pixels covered by either mask (union). Here, intersection is 3 and union is 6, so IoU = 3/6 = 0.50.

🧠 Conceptual

intermediate

Understanding Dice coefficient properties

Which of the following statements about the Dice coefficient is TRUE?

A Dice coefficient can be negative if masks have no overlap.

B Dice coefficient measures the difference between masks, not overlap.

C Dice coefficient is always smaller than IoU for the same masks.

D Dice coefficient equals 1 when two masks are identical.

💡 Hint

Think about what perfect overlap means for Dice.

Dice coefficient ranges from 0 to 1, with 1 meaning perfect overlap (identical masks). It cannot be negative. Dice is usually larger than IoU for the same masks.

❓ Metrics

advanced

Calculate Dice coefficient from confusion matrix values

Given true positives (TP)=30, false positives (FP)=10, and false negatives (FN)=20, what is the Dice coefficient?

A 0.67

B 0.60

C 0.75

D 0.80

💡 Hint

Dice = 2 * TP / (2 * TP + FP + FN)

Dice = 2*30 / (2*30 + 10 + 20) = 60 / 90 = 0.67

🔧 Debug

advanced

Identify the error in IoU calculation code

What error does the following code produce when calculating IoU for two numpy arrays mask1 and mask2?

Computer Vision

intersection = (mask1 & mask2).sum()
union = (mask1 | mask2).sum()
iou = intersection / union
print(iou)

A ZeroDivisionError if union is zero

B ValueError due to shape mismatch of mask1 and mask2

C TypeError because bitwise operators cannot be used on numpy arrays

D No error, code runs correctly and prints IoU

💡 Hint

Consider what happens if both masks are empty.

If both masks are empty, union is zero causing division by zero error.

❓ Model Choice

expert

Choosing the best metric for imbalanced segmentation

You have a segmentation task where the object occupies only 1% of the image pixels. Which metric is most reliable to evaluate your model's performance?

A IoU, because it balances false positives and false negatives

B Accuracy, because it measures overall pixel correctness

C Dice coefficient, because it is sensitive to small object overlap

D Mean Squared Error, because it measures pixel intensity differences

💡 Hint

Think about which metric handles small object sizes better.

Dice coefficient is more sensitive to overlap in small objects and less biased by large background pixels than accuracy or MSE.