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.