Machine learningMachine learning

Aktivno učenje sa samostalnim nadzorom učenja

Aktivno učenje u kombinaciji sa samostalnim nadzorom učenja iskorištava neoznačene podatke putem pretreniranja sa samostalnim nadzorom kako bi se izgradile bogate reprezentacije, a zatim koristi strategiju aktivnog upita za odabir najinformativnijih primjera za ljudsku anotaciju, maksimizirajući performanse modela pod strogo ograničenim budžetom za označavanje. Ovaj hibridni pristup posebno je snažan kada su označeni podaci rijetki, ali postoje veliki neoznačeni skupovi.

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. Bengar, J. Z., van de Weijer, J., Fuentes, L. L., & Raducanu, B. (2022). Class-Balanced Active Learning for Image Classification. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 3082–3091. link
  2. Wang, K., Zhang, D., Li, Y., Zhang, R., & Lin, L. (2016). Cost-Effective Active Learning for Deep Image Classification. IEEE Transactions on Circuits and Systems for Video Technology, 27(12), 2591–2600. DOI: 10.1109/TCSVT.2016.2589879

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Active Learning with Self-supervised Representation Learning. ScholarGate. https://scholargate.app/hr/machine-learning/active-learning-self-supervised-learning

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
ScholarGateActive Learning Self-supervised Learning (Active Learning with Self-supervised Representation Learning). Preuzeto 2026-06-15 s https://scholargate.app/hr/machine-learning/active-learning-self-supervised-learning · Skup podataka: https://doi.org/10.5281/zenodo.20539026