방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 준지도 학습 트랜스포머× | 준지도학습 합성곱 신경망× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2018–2019 | 2013–2017 |
| 창시자≠ | Devlin, J. et al. (BERT); broader SSL-Transformer paradigm community | Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others) |
| 유형 | Semi-supervised deep learning | Semi-supervised deep learning |
| 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 ↗ | 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. link ↗ |
| 별칭 | 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 |
| 관련 | 5 | 5 |
| 요약≠ | 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. |
| ScholarGate데이터셋 ↗ |
|
|