השוואת שיטות

	טרנספורמר בלמידה חצי-מפוקחת	רשת קונבולוציה למידה-מונחית-למחצה
תחום	למידה עמוקה	למידה עמוקה
משפחה	Machine learning	Machine learning
שנת המקור	2018–2019	2013–2017
הוגה השיטה	Devlin, J. et al. (BERT); broader SSL-Transformer paradigm community	Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others)
סוג	Semi-supervised deep learning	Semi-supervised deep learning
מקור מכונן	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT 2019, 4171–4186.	Lee, D.-H. (2013). Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. ICML Workshop on Challenges in Representation Learning.
כינויים	semi-supervised transformer model, SSL transformer, transformer with self-supervised pre-training, semi-supervised attention model	SSL-CNN, semi-supervised CNN, self-training CNN, pseudo-label CNN
קשורות	5	5
תקציר	Semi-supervised learning with Transformer architectures leverages large quantities of unlabeled data alongside a small labeled set to train powerful sequence models. The dominant pattern — exemplified by BERT — first pre-trains the Transformer on unlabeled data using self-supervised objectives such as masked token prediction, then fine-tunes it on the labeled task. This two-stage approach dramatically reduces the labeled data needed to achieve strong performance.	A Semi-supervised CNN trains a convolutional network on a small labeled image set and a larger pool of unlabeled images simultaneously, using techniques such as pseudo-labeling and consistency regularization to extract supervisory signal from unlabeled data. This strategy closes much of the performance gap caused by scarce annotations without requiring additional human labeling effort.