Machine learningDeep learning / NLP / CV

Samonadzorovani varijacijski autoenkoder

Samonadzorovani varijacijski autoenkoder (SS-VAE) kombinira generativno učenje latentnog prostora standardnog VAE-a sa samonadzoriranim pretka zadacima — poput kontrastne augmentacije, maskirane rekonstrukcije ili predikcije rotacije — kako bi se iz podataka bez oznaka naučile bogatije, bolje razdvojene reprezentacije bez potrebe za ručnom anotacijom.

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. Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes. In Proceedings of the 2nd International Conference on Learning Representations (ICLR 2014). link
  2. Liu, X., Zhang, F., Hou, Z., Mian, L., Wang, Z., Zhang, J., & Tang, J. (2021). Self-Supervised Learning: Generative or Contrastive. IEEE Transactions on Knowledge and Data Engineering, 35(1), 857–876. DOI: 10.1109/TKDE.2021.3090866

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Self-supervised Variational Autoencoder (SS-VAE). ScholarGate. https://scholargate.app/hr/deep-learning/self-supervised-variational-autoencoder

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

ScholarGateSelf-supervised Variational Autoencoder (Self-supervised Variational Autoencoder (SS-VAE)). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/self-supervised-variational-autoencoder · Skup podataka: https://doi.org/10.5281/zenodo.20539026