Modern Vision: Detection, Segmentation and ViT

1 min
  1. Which output distinguishes detection from classification?
  2. What is IoU for?
  3. Which metric suits a per-pixel mask?
  4. How does a ViT turn an image into a sequence?
  5. [E] Why not compare mAP, accuracy and Dice as one and the same score?

Answers. 1. Localized boxes in addition to classes. 2. To measure overlap. 3. Per-class IoU or Dice. 4. It projects patches into tokens. 5. These metrics deal with different objects, geometries and matching rules.

Objective: go beyond whole-image classification.

Detection predicts classes and boxes; semantic segmentation assigns a class to each pixel; instance segmentation distinguishes objects of the same class.

Preview — the rest of the lesson is for enrolled readers.

Already enrolled with a code?

Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.

Sign inNo account yet? Create one
This lesson is part of the “Modern Deep Dives” module

The first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.

Subscribe — 19 $ US/monthBack to the outline
Are you a student on this course?

The code is tied to your account: sign in or create an account and it will be applied automatically when you come back.

No account yet? Create one