Machine learningDeep learning / NLP / CV

Polunadzorirana segmentacija instanci

Polunadzorirana segmentacija instanci obučava model za detekciju i razgraničavanje svake instance objekta u slici koristeći mali označeni skup i veliki korpus neoznačenih slika. Generiranjem pseudo-oznaka iz pouzdanih predviđanja na neoznačenim slikama i provođenjem dosljednosti pod augmentacijom, pristup postiže konkurentnu točnost maski uz djelić pune cijene 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. Hu, H., Wei, P., Zheng, H., Bai, X., Wei, Y., & Chen, Y. (2021). Semi-supervised Semantic Segmentation via Adaptive Equalization Learning. Advances in Neural Information Processing Systems (NeurIPS), 34, 22106–22118. link
  2. Xu, M., Zhang, Z., Wei, F., Hu, H., Bai, X., & Jiang, Y.-G. (2021). End-to-End Semi-Supervised Object Detection with Soft Teacher. IEEE/CVF International Conference on Computer Vision (ICCV), 3060–3069. link

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Semi-supervised Instance Segmentation. ScholarGate. https://scholargate.app/hr/deep-learning/semi-supervised-instance-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

Citirana u

ScholarGateSemi-supervised Instance Segmentation (Semi-supervised Instance Segmentation). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/semi-supervised-instance-segmentation · Skup podataka: https://doi.org/10.5281/zenodo.20539026