Module 4 · Computer Vision with Deep Learning
Image Segmentation: lessons
Classification per pixel: semantic and instance segmentation, U-Net, and general segmentation models.
3 lessons · 46 min
What this module teaches, what it asks of you first and how you practise it are on its syllabus page.
Open the syllabusSemantic vs Instance Segmentation
14 minLabels per pixel, masks per object, and the metrics for each.
Included with the track Simulation insideU-Net
18 minThe encoder, the decoder, and the skip connections that bring back detail.
Included with the track Simulation insidePromptable Segmentation Models
14 minGeneral models that segment anything from a click or a box.
Included with the track