Σύγκριση μεθόδων

	Βελτιστοποιημένο Συνελικτικό Νευρωνικό Δίκτυο	Εκμάθηση Μεταφοράς με Συνελικτικά Νευρωνικά Δίκτυα
Πεδίο	Βαθιά Μάθηση	Βαθιά Μάθηση
Οικογένεια	Machine learning	Machine learning
Έτος προέλευσης	2012–2014	2010–2014
Δημιουργός	Yosinski, J. et al. (theoretical basis); practice widespread from Krizhevsky et al. 2012 onward	Pan, S. J. & Yang, Q. (transfer learning framework); popularized for CNNs by Yosinski et al. and Razavian et al.
Τύπος	Transfer learning technique (supervised fine-tuning)	Transfer learning applied to convolutional neural networks
Θεμελιώδης πηγή	Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems, 27.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Εναλλακτικές ονομασίες	Fine-tuned CNN, CNN fine-tuning, CNN transfer learning with fine-tuning, adapted convolutional network	TL-CNN, pretrained CNN, CNN fine-tuning, feature-extracting CNN
Συναφείς	5	4
Σύνοψη	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.	Transfer Learning with CNN reuses a convolutional neural network that has already been trained on a large dataset — most commonly ImageNet — and adapts its learned feature detectors to a new, often smaller target dataset. This lets researchers achieve strong image-recognition performance without the massive compute and data resources required to train a CNN from scratch.