방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 자가 지도 합성곱 신경망× | 준지도학습 합성곱 신경망× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2018–2020 | 2013–2017 |
| 창시자≠ | LeCun, Y. (CNN backbone); Chen et al. and He et al. (self-supervised visual frameworks) | Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others) |
| 유형≠ | Self-supervised deep learning | Semi-supervised deep learning |
| 원전≠ | 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. link ↗ | 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 | Self-supervised CNN, SSL-CNN, contrastive CNN, pretext-task CNN | SSL-CNN, semi-supervised CNN, self-training CNN, pseudo-label CNN |
| 관련 | 5 | 5 |
| 요약≠ | 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. | 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 ↗ |
|
|