Salīdzināt metodes

	Puss-uzraudzīta attēlu klasifikācija	Sīkāka pielāgošana attēlu klasifikācijai
Nozare	Dziļā mācīšanās	Dziļā mācīšanās
Saime	Machine learning	Machine learning
Izcelsmes gads	2013–2020	2010–2014
Autors	Lee, D.-H. (pseudo-label); Sohn et al. (FixMatch)	Yosinski, J. et al.; Pan, S. J. & Yang, Q.
Tips	Semi-supervised deep learning	Transfer learning / fine-tuning
Pirmavots	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.
Citi nosaukumi	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
Saistītās	5	5
Kopsavilkums	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.