Machine learningDeep learning / NLP / CV

Samonadzirani GAN

Samonadzirani GAN (Self-supervised GAN) nadopunjuje standardnu generativnu suparničku mrežu (GAN) s jednim ili više samonadziranih pomoćnih zadataka — poput predviđanja rotacije slike ili pozicije zakrpe — koji stabiliziraju suparničko treniranje i rezultiraju diskriminatorom koji uči bogate, prenosive reprezentacije iz neoznačenih podataka bez potrebe za ručnim anotacijama.

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. Chen, T., Zhai, X., Ritter, M., Lucic, M., & Houlsby, N. (2019). Self-Supervised GANs via Auxiliary Rotation Loss. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12154–12163. 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 Generative Adversarial Network. ScholarGate. https://scholargate.app/hr/deep-learning/self-supervised-gan

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 GAN (Self-supervised Generative Adversarial Network). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/self-supervised-gan · Skup podataka: https://doi.org/10.5281/zenodo.20539026