방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| Self-supervised Transformer× | 파인튜닝 트랜스포머× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도 | 2017–2019 | 2017–2019 |
| 창시자≠ | 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. |
| 유형≠ | Self-supervised deep learning model | Transfer learning / supervised fine-tuning |
| 원전≠ | 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. DOI ↗ | 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. link ↗ |
| 별칭 | 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 |
| 관련≠ | 5 | 4 |
| 요약≠ | 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. |
| ScholarGate데이터셋 ↗ |
|
|