ScholarGate
Asistent
Machine learningMachine learning

Samonadzorovani K-means

Samonadzorovani K-means je tehnika klasterizacije koja kombinira K-means dodjelu sa samonadzoriranim učenjem reprezentacija. Model izmjenjuje klasterizaciju podataka bez oznaka u K grupa i korištenje tih dodjela klastera kao pseudo-oznaka za poboljšanje temeljne reprezentacije značajki, što rezultira sve koherentnijim klasterima bez ikakve ljudski anotirane stvarne istine.

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. Caron, M., Bojanowski, P., Joulin, A., & Douze, M. (2018). Deep Clustering for Unsupervised Learning of Visual Features. In Proceedings of the European Conference on Computer Vision (ECCV), 132–149. link
  2. Self-supervised learning. Wikipedia. link

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Self-supervised K-means Clustering. ScholarGate. https://scholargate.app/hr/machine-learning/self-supervised-k-means

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
ScholarGateSelf-supervised K-means (Self-supervised K-means Clustering). Preuzeto 2026-06-15 s https://scholargate.app/hr/machine-learning/self-supervised-k-means · Skup podataka: https://doi.org/10.5281/zenodo.20539026