ScholarGate
Asistent
Machine learning

Vizuelno kontrastno učenje

Vizuelno kontrastno učenje je pristup dubokog učenja bez nadzora — popularizovan okvirima kao što su SimCLR (Chen et al., 2020) i MoCo (He et al., 2020) — koji uči bogate reprezentacije slike bez oznaka, tako što spaja različite augmentacije iste slike i razdvaja različite slike. Ono pretvara veliki skup neoznačenih slika u koristan ekstraktor obeležja.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte celu metodu

Samo za članove

Prijavite se besplatnim nalogom da biste pročitali ovaj odeljak.

Prijavite se

Method map

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

Izvori

  1. Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. ICML. link
  2. He, K., Fan, H., Wu, Y., Xie, S. & Girshick, R. (2020). Momentum Contrast for Unsupervised Visual Representation Learning. CVPR. link

Kako citirati ovu stranicu

ScholarGate. (2026, June 1). Visual Contrastive Self-Supervised Learning (SimCLR / MoCo / BYOL). ScholarGate. https://scholargate.app/sr/deep-learning/contrastive-learning-dl

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

ScholarGateVisual Contrastive Learning (Visual Contrastive Self-Supervised Learning (SimCLR / MoCo / BYOL)). Preuzeto 2026-06-15 sa https://scholargate.app/sr/deep-learning/contrastive-learning-dl · Skup podataka: https://doi.org/10.5281/zenodo.20539026