Segmentation evaluation (IoU, Dice) in Computer Vision - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does IoU stand for in segmentation evaluation?

IoU stands for Intersection over Union. It measures how much the predicted segmentation overlaps with the true segmentation compared to their combined area.

beginner

How is the Dice coefficient calculated?

Dice coefficient = 2 × (Area of Overlap) / (Total number of pixels in both predicted and true segments). It ranges from 0 (no overlap) to 1 (perfect overlap).

intermediate

Why do we use both IoU and Dice for segmentation evaluation?

IoU and Dice both measure overlap but emphasize different aspects. Dice is more sensitive to small objects, while IoU is stricter. Using both gives a fuller picture of model performance.

beginner

What does an IoU score of 0.7 mean?

An IoU of 0.7 means the predicted and true segments overlap by 70% of their combined area. This indicates good but not perfect segmentation.

intermediate

Write the formula for IoU using sets A (prediction) and B (ground truth).

IoU = |A ∩ B| / |A ∪ B|, where |A ∩ B| is the number of pixels in both prediction and ground truth, and |A ∪ B| is the number of pixels in either prediction or ground truth.

What does a Dice coefficient of 1 indicate?

A No overlap between prediction and ground truth

B Prediction is half the size of ground truth

C Prediction is twice the size of ground truth

D Perfect overlap between prediction and ground truth

A Dice coefficient of 1 means the predicted and true segments perfectly overlap.

Which metric is calculated as the intersection over the union of predicted and true segments?

A Accuracy

B IoU

C Dice coefficient

D Precision

IoU is defined as the intersection area divided by the union area of prediction and ground truth.

If the predicted segmentation is completely outside the true segmentation, what is the IoU score?

A 0

B 1

C 0.5

D Cannot be determined

No overlap means intersection is zero, so IoU is zero.

Which metric tends to give higher values for small objects in segmentation?

A IoU

B Accuracy

C Dice coefficient

D Recall

Dice coefficient is more sensitive and tends to give higher scores for small objects.

What is the range of values for both IoU and Dice coefficient?

A 0 to 1

B 0 to 100

C -1 to 1

D -100 to 100

Both IoU and Dice range from 0 (no overlap) to 1 (perfect overlap).

Explain in your own words what Intersection over Union (IoU) measures in segmentation tasks.

Think about how much the predicted area and true area share in common compared to their total combined area.

Describe the difference between Dice coefficient and IoU and why both are useful for evaluating segmentation models.

Consider how each metric treats overlap and size differences.

Practice

1. What does the Intersection over Union (IoU) metric measure in image segmentation?

easy

A. The overlap between predicted and true masks divided by their union

B. The difference between predicted and true masks

C. The total number of pixels in the predicted mask

D. The ratio of true positives to false negatives

Solution

1. Step 1: Understand IoU definition

   IoU measures how much the predicted mask and true mask overlap compared to their combined area.

2. Step 2: Apply IoU formula

   IoU = (Area of Overlap) / (Area of Union) between predicted and true masks.

3. Final Answer:

   The overlap between predicted and true masks divided by their union -> Option A

4. Quick Check:

   IoU = Overlap / Union [OK]

Hint: IoU = Overlap divided by combined area [OK]

Common Mistakes:

• Confusing IoU with difference or subtraction
• Using only predicted mask area
• Mixing IoU with accuracy or precision

2. Which of the following is the correct formula for Dice coefficient between predicted mask P and true mask T?

easy

A. Dice = |P| / |T|

B. Dice = (2 * |P ∩ T|) / (|P| + |T|)

C. Dice = |P ∪ T| / (|P| + |T|)

D. Dice = |P ∩ T| / |P ∪ T|

Solution

1. Step 1: Recall Dice coefficient formula

   Dice coefficient is defined as twice the overlap divided by the sum of sizes of predicted and true masks.

2. Step 2: Match formula to options

   Dice = (2 * |P ∩ T|) / (|P| + |T|) matches Dice = (2 * intersection) / (sum of areas).

3. Final Answer:

   Dice = (2 * |P ∩ T|) / (|P| + |T|) -> Option B

4. Quick Check:

   Dice = 2*Overlap / (Sum areas) [OK]

Hint: Dice doubles overlap, divides by sum of mask sizes [OK]

Common Mistakes:

• Confusing Dice with IoU formula
• Using union instead of sum of areas
• Forgetting to multiply overlap by 2

3. Given predicted mask pixels: {1,2,3,4} and true mask pixels: {3,4,5,6}, what is the IoU score?

medium

A. 0.33

B. 0.25

C. 0.5

D. 0.4

Solution

1. Step 1: Calculate intersection and union

   Intersection = {3,4} size = 2; Union = {1,2,3,4,5,6} size = 6.

2. Step 2: Compute IoU

   IoU = Intersection / Union = 2 / 6 = 0.3333 (approx). Check options carefully.

3. Step 3: Re-check options

   0.33 is 0.33, closest to calculation. But 0.4 is 0.4, which is incorrect.

4. Final Answer:

   0.33 -> Option A

5. Quick Check:

   IoU = 2/6 = 0.33 [OK]

Hint: IoU = intersection size / union size [OK]

Common Mistakes:

• Counting union incorrectly
• Mixing intersection with union
• Rounding IoU incorrectly

4. You have this Python code to compute Dice score but it returns 0. Identify the error:

def dice_score(pred, true):
    intersection = len(pred & true)
    return intersection / (len(pred) + len(true))

pred = {1,2,3}
true = {2,3,4}
print(dice_score(pred, true))

medium

A. Wrong variable names in function

B. Using set intersection instead of union

C. Incorrect data type for masks

D. Missing multiplication by 2 in numerator

Solution

1. Step 1: Review Dice formula

   Dice = 2 * intersection / (sum of sizes). The code misses multiplying intersection by 2.

2. Step 2: Check code calculation

   Code returns intersection / sum, which is half the correct Dice score.

3. Final Answer:

   Missing multiplication by 2 in numerator -> Option D

4. Quick Check:

   Dice needs 2*intersection [OK]

Hint: Dice numerator must be 2 times intersection [OK]

Common Mistakes:

• Forgetting to multiply intersection by 2
• Confusing intersection with union
• Using wrong data types for masks

5. A segmentation model predicts a mask with 80 pixels, the true mask has 100 pixels, and their overlap is 60 pixels. What is the Dice score and IoU score respectively?

hard

A. Dice = 0.8, IoU = 0.7

B. Dice = 0.75, IoU = 0.6

C. Dice = 0.67, IoU = 0.5

D. Dice = 0.6, IoU = 0.75

Solution

1. Step 1: Calculate Dice score

   Dice = 2 * overlap / (predicted + true) = 2*60 / (80+100) = 120/180 = 0.6667 (approx). Check options carefully.

2. Step 2: Calculate IoU score

   IoU = overlap / union = 60 / (80 + 100 - 60) = 60 / 120 = 0.5.

3. Step 3: Re-check options

   Dice = 0.67, IoU = 0.5 matches Dice ~0.67 and IoU 0.5 exactly.

4. Final Answer:

   Dice = 0.67, IoU = 0.5 -> Option C

5. Quick Check:

   Dice = 2*60/180=0.67, IoU=60/120=0.5 [OK]

Hint: Dice doubles overlap; IoU divides by union [OK]

Common Mistakes:

• Using sum instead of union for IoU denominator
• Forgetting to multiply overlap by 2 for Dice
• Mixing Dice and IoU formulas