ScholarGate
Pembantu
Machine learningMachine learning

Pembelajaran Pindahan Kendiri Seliaan

Pembelajaran pindahan kendiri seliaan menggabungkan dua paradigma berkuasa: model mula-mula mempelajari perwakilan yang kaya daripada data tidak berlabel menggunakan tugas preteks kendiri seliaan, kemudian perwakilan yang dipelajari itu dipindahkan dan ditala halus pada tugas hiliran dengan data berlabel yang terhad. Pendekatan ini mendasari sistem mercu tanda seperti BERT dalam NLP dan SimCLR serta DINO dalam penglihatan komputer, mengurangkan keperluan data berlabel secara mendadak merentasi banyak domain.

Buka dalam MethodMindTidak lama lagiVideoTidak lama lagiDownload slides

Baca kaedah sepenuhnya

Ahli sahaja

Log masuk dengan akaun percuma untuk membaca bahagian ini.

Log masuk

Method map

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

Sumber

  1. 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
  2. Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT 2019, 4171–4186. Association for Computational Linguistics. DOI: 10.18653/v1/N19-1423

Cara memetik halaman ini

ScholarGate. (2026, June 3). Self-supervised Pre-training for Transfer Learning. ScholarGate. https://scholargate.app/ms/machine-learning/self-supervised-transfer-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
ScholarGateSelf-supervised Transfer learning (Self-supervised Pre-training for Transfer Learning). Dicapai 2026-06-15 daripada https://scholargate.app/ms/machine-learning/self-supervised-transfer-learning · Set data: https://doi.org/10.5281/zenodo.20539026