quiz bu lëkkale ak tegtal · Dëgër Niveau

Swin

Saytu palanteer yuñ toxal, jokkoog palanteer yu bari, man-mani hierarchique, boole ay patch, ak aplikaasioŋu liggéeyu gis-gis ci Swin.

Yooni njiit yu jëm ciTransformatër Swin
Laaj 1 de 8

Luy 'Swin' ci Transformateur Swin?

Xoolaatal laaj bu nekk8 laaj

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

  1. Luy 'Swin' ci Transformateur Swin?
    • Windows yuñ toxal
    • Palanteer bu nooy
    • Enroulement spatial
    • Benn Palanteer
  2. What positional information does Swin add within each local attention window?
    • Absolute word embeddings from a text tokenizer
    • A learnable relative-position bias
    • A global convolution kernel shared across all windows
    • A class-specific bounding-box regression target
  3. Naka lay def ba Swin may leeral yi ñu toxu ci diggante palanteer yu wuute?
    • Dafay jëfandikoo lëkkaloo yuy baaxoo
    • Dafay efaase palanteer yépp
    • Dafay soppi xaaj bu palanteer bi ci ay diisaay yuy wuutale
    • Benn palanteer global rek lay jëfandikoo
  4. Lan la couche yuy boole ay patch di def ci digganté etape Swin yi?
    • Yokk dayo te dindi chaine yi
    • Dëddu ay patch ci anam wu mucc
    • Tekki patch yi ci kàddu
    • boole patch yi ci wetam, wàññi dayo bi ak yokk chaine yi
  5. Lan moo waral génnug Swin ci wàllu hierarchie, bari eskaal am njariñ?
    • Dafay boole bu baax ci gis-gis ak kaadar segmentation yiy seentu piramidu man-man
    • Dafay jàppale ci xaaj bu am benn etiket
    • Dina dindi soxla done yuñ etikete
    • Dafay tax model bi gëna ndaw ci bépp CNN
  6. How does Swin’s attention pattern differ from standard ViT attention?
    • Swin has no attention mechanism
    • Swin computes attention in local windows and shifts partitions between blocks; standard ViT uses global patch attention
    • ViT uses only local convolutions
    • Both always use identical global attention
  7. What scaling property does fixed-size window attention provide in Swin?
    • It is independent of image resolution
    • It becomes quadratic in channel count only
    • Attention computation grows linearly with image size for fixed window size
    • It removes all attention computation
  8. Why does shifted-window attention use a mask after the cyclic shift?
    • To force every patch to attend to every image patch
    • To remove all positional information
    • To convert window attention into a convolution
    • To prevent tokens from attending across boundaries that should remain separate windows