ScholarGate
Assistent
Machine learningDeep learning / NLP / CV

Semi-overvåget billedklassifikation

Semi-overvåget billedklassifikation træner dybe neurale netværk på et lille sæt mærkede billeder sammen med en meget større pulje af umærkede billeder. Teknikker som pseudo-mærkning, konsistensregularisering og konfidens-tærskelværdi gør det muligt for modellen at udnytte strukturen af umærkede data, hvilket dramatisk reducerer behovet for dyr manuel annotering, mens den nærmer sig fuldt-overvåget nøjagtighed.

Åbn i MethodMindSnartVideoSnartDownload slides

Læs hele metoden

Kun for medlemmer

Log ind med en gratis konto for at læse dette afsnit.

Log ind

Method map

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

Kilder

  1. Lee, D.-H. (2013). Pseudo-Label: The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks. ICML 2013 Workshop on Challenges in Representation Learning. link
  2. Sohn, K., Berthelot, D., Li, C.-L., Zhang, Z., Carlini, N., Cubuk, E. D., Kurakin, A., Zhang, H., & Raffel, C. (2020). FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence. Advances in Neural Information Processing Systems, 33, 596–608. link

Sådan citerer du denne side

ScholarGate. (2026, June 3). Semi-supervised Image Classification with Deep Neural Networks. ScholarGate. https://scholargate.app/da/deep-learning/semi-supervised-image-classification

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

Refereret af

ScholarGateSemi-supervised Image Classification (Semi-supervised Image Classification with Deep Neural Networks). Hentet 2026-06-15 fra https://scholargate.app/da/deep-learning/semi-supervised-image-classification · Datasæt: https://doi.org/10.5281/zenodo.20539026