Porównaj metody
Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.
| Uczenie transferowe z samo-nadzorem× | Samonadzorowane uczenie z niewielką liczbą przykładów× | |
|---|---|---|
| Dziedzina | Uczenie maszynowe | Uczenie maszynowe |
| Rodzina | Machine learning | Machine learning |
| Rok powstania≠ | 2018–2020 (modern consolidation) | 2019 |
| Twórca≠ | LeCun, Y. (concept); Devlin et al. (BERT, NLP); Chen et al. (SimCLR, vision) | Gidaris, S. et al.; Su, J.-C. et al. (concurrent seminal works) |
| Typ≠ | Learning paradigm (self-supervised pre-training + fine-tuning) | Hybrid learning paradigm (self-supervised pretraining + few-shot adaptation) |
| Źródło pierwotne≠ | Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In Proceedings of the 37th International Conference on Machine Learning (ICML), PMLR 119, 1597–1607. link ↗ | 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 ↗ |
| Inne nazwy | self-supervised pre-training, SSL-based transfer learning, representation transfer from self-supervised models, contrastive pre-training with transfer | SSL-FSL, self-supervised meta-learning, unsupervised few-shot learning, self-supervised prototypical learning |
| Pokrewne≠ | 6 | 2 |
| Podsumowanie≠ | Self-supervised transfer learning combines two powerful paradigms: a model first learns rich representations from unlabeled data using self-supervised pretext tasks, then those learned representations are transferred and fine-tuned on a downstream task with limited labeled data. This approach underlies landmark systems such as BERT in NLP and SimCLR and DINO in computer vision, dramatically reducing labeled-data requirements across many domains. | Self-supervised Few-shot Learning (SSL-FSL) combines self-supervised pretraining on large unlabeled corpora with few-shot meta-learning so that a model can recognize new categories from only a handful of labeled examples. By learning rich, transferable representations without expensive annotation, SSL-FSL addresses the fundamental bottleneck of supervised few-shot methods: the need for labeled support data at scale. |
| ScholarGateZbiór danych ↗ |
|
|