Machine learningDeep learning / NLP / CV

Objašnjivi Vision Transformer

Objašnjivi Vision Transformer (Explainable Vision Transformer) kombinira snažne performanse Vision Transformersa (ViT) u prepoznavanju slika s tehnikama atribucije — kao što su propagacija relevantnosti, raspakiravanje pažnje (attention rollout) ili težinska pažnja temeljena na gradijentu (gradient-weighted attention) — koje ističu koje regije slike pokreću svaku predikciju. Pristup omogućuje istraživačima i praktičarima reviziju odluka modela i ispunjavanje zahtjeva za transparentnošću bez žrtvovanja točnosti.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte cijelu metodu

Samo za članove

Prijavite se besplatnim računom kako biste pročitali ovaj odjeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

Izvori

  1. Chefer, H., Gur, S., & Wolf, L. (2021). Transformer interpretability beyond attention visualization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 782–791. DOI: 10.1109/CVPR46437.2021.00084
  2. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., … Houlsby, N. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations (ICLR). link

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Explainable Vision Transformer (XViT / ViT with Post-hoc Attribution). ScholarGate. https://scholargate.app/hr/deep-learning/explainable-vision-transformer

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Citirana u

ScholarGateExplainable Vision Transformer (Explainable Vision Transformer (XViT / ViT with Post-hoc Attribution)). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/explainable-vision-transformer · Skup podataka: https://doi.org/10.5281/zenodo.20539026