Σύγκριση μεθόδων

	Ημι-εποπτευόμενο Συνελικτικό Νευρωνικό Δίκτυο	Βελτιστοποιημένο Συνελικτικό Νευρωνικό Δίκτυο
Πεδίο	Βαθιά Μάθηση	Βαθιά Μάθηση
Οικογένεια	Machine learning	Machine learning
Έτος προέλευσης	2013–2017	2012–2014
Δημιουργός	Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others)	Yosinski, J. et al. (theoretical basis); practice widespread from Krizhevsky et al. 2012 onward
Τύπος	Semi-supervised deep learning	Transfer learning technique (supervised fine-tuning)
Θεμελιώδης πηγή	Lee, D.-H. (2013). Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. ICML 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, 27.
Εναλλακτικές ονομασίες	SSL-CNN, semi-supervised CNN, self-training CNN, pseudo-label CNN	Fine-tuned CNN, CNN fine-tuning, CNN transfer learning with fine-tuning, adapted convolutional network
Συναφείς	5	5
Σύνοψη	A Semi-supervised CNN trains a convolutional network on a small labeled image set and a larger pool of unlabeled images simultaneously, using techniques such as pseudo-labeling and consistency regularization to extract supervisory signal from unlabeled data. This strategy closes much of the performance gap caused by scarce annotations without requiring additional human labeling effort.	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.