Comparer des méthodes

	Classification d'images par réglage fin	Réseau neuronal convolutif affiné
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2010–2014	2012–2014
Auteur d'origine	Yosinski, J. et al.; Pan, S. J. & Yang, Q.	Yosinski, J. et al. (theoretical basis); practice widespread from Krizhevsky et al. 2012 onward
Type	Transfer learning / fine-tuning	Transfer learning technique (supervised fine-tuning)
Source fondatrice	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.	Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems, 27.
Alias	fine-tuning for image recognition, transfer learning image classifier, pretrained CNN fine-tuning, domain-specific image classifier	Fine-tuned CNN, CNN fine-tuning, CNN transfer learning with fine-tuning, adapted convolutional network
Apparentées	5	5
Résumé	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.	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.