Machine learningMachine learning

Samonadgledano učenje sa malo primera

Samonadgledano učenje sa malo primera (SSL-FSL) kombinuje samonadgledano pred-treniranje na velikim neoznačenim korpusima sa meta-učenjem sa malo primera, tako da model može da prepozna nove kategorije iz samo nekolicine označenih primera. Učeći bogate, prenosive reprezentacije bez skupih anotacija, SSL-FSL rešava fundamentalno usko grlo nadgledanih metoda sa malo primera: potrebu za označenim potpornim podacima u velikom obimu.

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. Gidaris, S., Bursuc, A., Komodakis, N., Perez, P., & Cord, M. (2019). Boosting Few-Shot Visual Learning with Self-Supervision. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 8059–8068. DOI: 10.1109/ICCV.2019.00815
  2. Su, J.-C., Maji, S., & Hariharan, B. (2020). When Does Self-Supervision Improve Few-Shot Learning? European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, vol 12371, 645–660. DOI: 10.1007/978-3-030-58571-6_38

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Self-supervised Few-shot Learning (SSL-FSL). ScholarGate. https://scholargate.app/sr/machine-learning/self-supervised-few-shot-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

Citirana u

ScholarGateSelf-supervised Few-shot Learning (Self-supervised Few-shot Learning (SSL-FSL)). Preuzeto 2026-06-15 sa https://scholargate.app/sr/machine-learning/self-supervised-few-shot-learning · Skup podataka: https://doi.org/10.5281/zenodo.20539026