방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 준지도 학습 이미지 분류× | 이미지 분류를 위한 전이 학습× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2013–2020 | 2010–2012 |
| 창시자≠ | Lee, D.-H. (pseudo-label); Sohn et al. (FixMatch) | Pan, S. J. & Yang, Q. (transfer learning framework); Krizhevsky, Sutskever & Hinton (deep CNN backbone) |
| 유형≠ | Semi-supervised deep learning | Transfer learning / supervised classification |
| 원전≠ | Lee, D.-H. (2013). Pseudo-Label: The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks. ICML 2013 Workshop on Challenges in Representation Learning. link ↗ | Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI ↗ |
| 별칭 | SSL image classification, semi-supervised CNN classification, pseudo-label image classification, label-efficient image classification | pretrained CNN image classification, fine-tuned image classifier, domain-adapted image classifier, TL-IC |
| 관련≠ | 5 | 4 |
| 요약≠ | Semi-supervised image classification trains deep neural networks on a small set of labeled images together with a much larger pool of unlabeled images. Techniques such as pseudo-labeling, consistency regularization, and confidence thresholding allow the model to leverage the structure of unlabeled data, dramatically reducing the need for expensive manual annotation while approaching fully-supervised accuracy. | Transfer Learning with Image Classification reuses a deep neural network backbone — typically a CNN or Vision Transformer — pretrained on a large dataset such as ImageNet, and adapts it to classify images in a new target domain. By inheriting general visual features from the source task, the approach achieves high accuracy with far fewer labeled images than training from scratch. |
| ScholarGate데이터셋 ↗ |
|
|