Сравнение методов

	Обучение с переносом для классификации изображений	Дообученная (fine-tuned) свёрточная нейронная сеть
Область	Глубокое обучение	Глубокое обучение
Семейство	Machine learning	Machine learning
Год появления	2010–2012	2012–2014
Автор метода	Pan, S. J. & Yang, Q. (transfer learning framework); Krizhevsky, Sutskever & Hinton (deep CNN backbone)	Yosinski, J. et al. (theoretical basis); practice widespread from Krizhevsky et al. 2012 onward
Тип	Transfer learning / supervised classification	Transfer learning technique (supervised fine-tuning)
Основополагающий источник	Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.	Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems, 27.
Другие названия	pretrained CNN image classification, fine-tuned image classifier, domain-adapted image classifier, TL-IC	Fine-tuned CNN, CNN fine-tuning, CNN transfer learning with fine-tuning, adapted convolutional network
Связанные	4	5
Сводка	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.	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.