Laaj ak tontu ci tabax U-Net

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. Lan moo jox U-Net jëmmu 'U'?
   • Encodeur buy wàññi échantillons ak decodeur symétrique buy yokk échantillons
   • Benn pilu konvolusioŋ bu jub
   • Ñaari reso yu paralel te amul benn lëkkaloo
   • ab bouclage buy dellusi ci diir bi
2. Luy sabab bi U-Net di sànni lëkkaloo yi?
   • ngir wàññi limu parametre yi ba amul dara
   • Ngir joxe ay detay yu ndaw ci wàllu encodeur yi ci couche decodeur yi méngoo
   • Ngir soppi nataal bi ci grayscale
   • ngir teggi tàggat yaram
3. Lu ñu njëkka sos U-Net?
   • Xamme kàddu
   • Xalaatal njëgu action yi
   • Taxawaayu nataalu biomédikal
   • Tekki làkku mbind
4. Ci diffusion stable, lan la U-Net di wax ci jéego bu nekk?
   • Kapsioŋ bu mujj ci nataal bi
   • Rasio kompresioŋ
   • Angle kamera bi
   • Bruit bi nga wara dindi ci bruit bu nëbbu bi
5. Lan mooy dall ci leerali barab yi encoder bi di wàññi samples yi?
   • Dafay dindi 'li' am waaye dafay ñàkk ay detay 'fan' yu leer
   • Dafay am barabu pixel yi
   • Dafay soppi nataal bi def ko bind
   • Dafay yokk dayo bi ñaari yoon
6. Which augmentation did the original U-Net paper use to learn invariance from limited annotated biomedical images?
   • Replacing every image with a random label
   • Elastic deformations of the training images
   • Training only on unmodified test images
   • Removing the decoder path before training
7. How did the original U-Net paper process large images beyond the network’s input size?
   • By discarding all image borders
   • By resizing every image to one pixel
   • By predicting on overlapping tiles and extrapolating context at tile borders
   • By running the model once on a text prompt
8. What did the original U-Net paper’s weighted loss emphasize?
   • Only background pixels, regardless of distance
   • The most common image color
   • Noise prediction at a diffusion timestep
   • Border pixels between touching cells to help separate adjacent objects