@pfjaeger : In 25021, we published nnU-Net addressing an ongoing bias towards novel architectures in medical image segmentation. Now, 3 years later, we observe that this innovation bias prevails, and - despite recent claims - scaled U-Net variants remain SotA, at least on current benchmarks. • TwiCopy

Paul F. Jaeger

@pfjaeger

+ Follow

Health AI Research at @GoogleDeepMind. Ex- @DKFZ, @KIT, @ELLISforEurope, and @AIatMeta.

ID: 3095894499

linkhttp://pfjaeger.github.io calendar_today19-03-2015 03:54:47

250 Tweet

799 Followers

308 Following

Paul F. Jaeger

@pfjaeger

a year ago

In 2021, we published nnU-Net addressing an ongoing bias towards novel architectures in medical image segmentation. Now, 3 years later, we observe that this innovation bias prevails, and - despite recent claims - scaled U-Net variants remain SotA, at least on current benchmarks.

thumb_up_off_alt40

chat_bubble_outline1

repeat5

shareShare