So sánh phương pháp

	Phân loại ảnh bán giám sát	Phân loại ảnh tinh chỉnh
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2013–2020	2010–2014
Người khởi xướng	Lee, D.-H. (pseudo-label); Sohn et al. (FixMatch)	Yosinski, J. et al.; Pan, S. J. & Yang, Q.
Loại	Semi-supervised deep learning	Transfer learning / fine-tuning
Công trình gốc	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.	Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems (NeurIPS), 27, 3320–3328.
Tên gọi khác	SSL image classification, semi-supervised CNN classification, pseudo-label image classification, label-efficient image classification	fine-tuning for image recognition, transfer learning image classifier, pretrained CNN fine-tuning, domain-specific image classifier
Liên quan	5	5
Tóm tắt	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.	Fine-tuned image classification adapts a large neural network pretrained on a broad image corpus (such as ImageNet) to a specific target domain by continuing training on labeled domain images. This approach achieves strong accuracy with far fewer target-domain samples than training from scratch, making it the dominant paradigm for applied computer vision tasks.