Machine learningDeep learning / NLP / CV

Polunadzorirana semantička segmentacija

Polunadzorirana semantička segmentacija obučava modele za etiketiranje na razini piksela koristeći mali skup potpuno označenih slika u kombinaciji s mnogo većim skupom neoznačenih slika. Tehnike poput pseudo-etiketiranja i regularizacije dosljednosti izvlače nadzorni signal iz neoznačenih podataka, omogućujući postizanje gotovo potpuno nadzirane točnosti uz djelić troškova anotacije.

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. Ouali, Y., Hudelot, C., & Tami, M. (2020). Semi-Supervised Semantic Segmentation with Cross-Consistency Training. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12674–12684. DOI: 10.1109/CVPR42600.2020.01269
  2. Zou, Y., Zhang, Z., Zhang, H., Li, C.-L., Bian, X., Huang, J.-B., & Pfister, T. (2020). PseudoSeg: Designing Pseudo Labels for Semantic Segmentation. International Conference on Learning Representations (ICLR 2021). link

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Semi-supervised Semantic Segmentation (Pseudo-label and Consistency-based). ScholarGate. https://scholargate.app/hr/deep-learning/semi-supervised-semantic-segmentation

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
ScholarGateSemi-supervised Semantic Segmentation (Semi-supervised Semantic Segmentation (Pseudo-label and Consistency-based)). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/semi-supervised-semantic-segmentation · Skup podataka: https://doi.org/10.5281/zenodo.20539026