Segmentation: U-Net and dense prediction

Segmentation: answer “what” for every pixel

Detection finds objects and draws boxes. Segmentation is finer: it assigns a class to every pixel. A CT slice is tumor vs healthy tissue vs background at pixel resolution—that is what medicine, autonomous driving, and satellite analysis need. U-Net (2015, biomedical imaging) became the default architecture for dense segmentation.

Full content is available with a subscription.

Get full access to all courses on the platform for one year with a single payment.

Unlike other platforms that charge per course, here you get everything for one price, and after one year of use there will be no automatic charge for the following year.