Comparer des méthodes

	Transformer auto-supervisé	Transformer affiné
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2017–2019	2017–2019
Auteur d'origine	Vaswani et al. (architecture); Devlin et al. (BERT self-supervised paradigm)	Vaswani et al. (architecture); fine-tuning paradigm popularised by Howard & Ruder, Devlin et al.
Type	Self-supervised deep learning model	Transfer learning / supervised fine-tuning
Source fondatrice	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.	Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.
Alias	SSL Transformer, self-supervised pretraining, masked self-attention pretraining, contrastive transformer	Transformer fine-tuning, pre-trained transformer fine-tuning, task-adaptive transformer, downstream-tuned transformer
Apparentées	5	4
Résumé	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.	Fine-tuning a Transformer adapts a large pre-trained model — such as BERT, GPT, or ViT — to a specific downstream task by continuing gradient-based training on a labelled target dataset. This two-stage paradigm (pre-train then fine-tune) consistently achieves state-of-the-art results across NLP and computer vision tasks with far less task-specific data than training from scratch.