← Back to curriculum

Module 5 — Image segmentation

Module 5 quiz & review

25 interactive questions on segmentation types, U-Net, DeepLab, Mask R-CNN, and IoU/Dice with lesson review links.

~60 min read + exercises

Module 5 quiz and review

Before we begin

Check segmentation types, encoder–decoder design, U-Net, other models (DeepLab, FCN), Mask R-CNN, and IoU/Dice before the project. Aim for at least 19 out of 25.


Multiple choice quiz

Interactive quiz

Pick one answer per question. Feedback appears immediately — take your time before clicking.

0 / 25 correct·0 answered
  1. Question 1 of 25

    Image segmentation differs from classification because:

    Answer options for question 1
  2. Question 2 of 25

    Semantic segmentation means:

    Answer options for question 2
  3. Question 3 of 25

    Instance segmentation adds what semantic segmentation cannot do?

    Answer options for question 3
  4. Question 4 of 25

    Panoptic segmentation combines:

    Answer options for question 4
  5. Question 5 of 25

    DeepLab ASPP (Atrous Spatial Pyramid Pooling) is designed to:

    Answer options for question 5
  6. Question 6 of 25

    Why is dense prediction harder than image classification?

    Answer options for question 6
  7. Question 7 of 25

    The key idea of U-Net skip connections is:

    Answer options for question 7
  8. Question 8 of 25

    In U-Net, the contracting path (encoder) mainly:

    Answer options for question 8
  9. Question 9 of 25

    The expanding path (decoder) in U-Net uses:

    Answer options for question 9
  10. Question 10 of 25

    U-Net was originally designed for:

    Answer options for question 10
  11. Question 11 of 25

    IoU (Intersection over Union) for a binary mask compares:

    Answer options for question 11
  12. Question 12 of 25

    Pixel accuracy alone can be misleading when:

    Answer options for question 12
  13. Question 13 of 25

    Dice coefficient is closely related to:

    Answer options for question 13
  14. Question 14 of 25

    For multi-class segmentation training, a typical loss is:

    Answer options for question 14
  15. Question 15 of 25

    Atrous (dilated) convolution in DeepLab mainly helps by:

    Answer options for question 15
  16. Question 16 of 25

    Portrait background removal in mobile apps is usually:

    Answer options for question 16
  17. Question 17 of 25

    After the final U-Net layer you typically apply:

    Answer options for question 17
  18. Question 18 of 25

    RoIAlign in Mask R-CNN improves on RoI Pooling because it:

    Answer options for question 18
  19. Question 19 of 25

    If predicted mask is entirely empty but ground truth has a large object, IoU is:

    Answer options for question 19
  20. Question 20 of 25

    Compared to a plain encoder–decoder without skips, U-Net usually:

    Answer options for question 20
  21. Question 21 of 25

    Mask R-CNN extends Faster R-CNN by adding:

    Answer options for question 21
  22. Question 22 of 25

    Object detection outputs ___ ; semantic segmentation outputs ___.

    Answer options for question 22
  23. Question 23 of 25

    Mean IoU (mIoU) across classes:

    Answer options for question 23
  24. Question 24 of 25

    A double conv block (conv → ReLU → conv → ReLU) in U-Net:

    Answer options for question 24
  25. Question 25 of 25

    A common reason to use pretrained DeepLab instead of scratch U-Net on natural photos is:

    Answer options for question 25

After the quiz

19/25 or higher? Start the U-Net segmentation project.

Checklist:

  • I can explain semantic vs instance segmentation.
  • I know why encoder–decoder networks upsample.
  • I can describe U-Net skip connections.
  • I can name when DeepLab or Mask R-CNN fits better than U-Net.
  • I can interpret IoU on a validation mask.

What's next

Project: U-Net pet segmentation