방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 준지도학습 합성곱 신경망× | 미세 조정된 합성곱 신경망× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2013–2017 | 2012–2014 |
| 창시자≠ | Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others) | Yosinski, J. et al. (theoretical basis); practice widespread from Krizhevsky et al. 2012 onward |
| 유형≠ | Semi-supervised deep learning | Transfer learning technique (supervised fine-tuning) |
| 원전≠ | 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 ↗ | Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems, 27. link ↗ |
| 별칭 | SSL-CNN, semi-supervised CNN, self-training CNN, pseudo-label CNN | Fine-tuned CNN, CNN fine-tuning, CNN transfer learning with fine-tuning, adapted convolutional network |
| 관련 | 5 | 5 |
| 요약≠ | 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. | Fine-tuning a CNN means starting from a network already trained on a large dataset — typically ImageNet — and continuing training on a smaller target dataset so the model adapts its learned visual features to a new task. This approach dramatically reduces the data and compute required to reach strong performance compared with training from scratch. |
| ScholarGate데이터셋 ↗ |
|
|