השוואת שיטות

	טרנספורמר למידה-עצמית	רשת קונבולוציה למידה עצמית-מונחית
תחום	למידה עמוקה	למידה עמוקה
משפחה	Machine learning	Machine learning
שנת המקור	2017–2019	2018–2020
הוגה השיטה	Vaswani et al. (architecture); Devlin et al. (BERT self-supervised paradigm)	LeCun, Y. (CNN backbone); Chen et al. and He et al. (self-supervised visual frameworks)
סוג	Self-supervised deep learning model	Self-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.	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 2020), PMLR 119, 1597–1607.
כינויים	SSL Transformer, self-supervised pretraining, masked self-attention pretraining, contrastive transformer	Self-supervised CNN, SSL-CNN, contrastive CNN, pretext-task CNN
קשורות	5	5
תקציר	A self-supervised Transformer is a Transformer network pretrained using automatically constructed supervision signals — such as masked token prediction or next-sentence prediction — rather than human-annotated labels. The resulting representations are then fine-tuned or probed on downstream tasks. BERT, GPT, and ViT (Vision Transformer in masked-image modeling mode) are the most widely known instantiations of this paradigm.	A self-supervised convolutional neural network (CNN) learns powerful visual representations from unlabeled images by solving pretext tasks — such as contrastive instance discrimination or masked-patch prediction — and then fine-tunes on a small labeled set. This approach dramatically reduces dependence on large annotated datasets while preserving the spatial feature-extraction strengths of convolutional architectures.