Comparer des méthodes

	Apprentissage par transfert avec détection d'objets	Réseau neuronal convolutif affiné
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2010–2014	2012–2014
Auteur d'origine	Girshick, R. et al. (R-CNN line); Pan & Yang (transfer learning framework)	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	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.
Alias	pretrained object detector, fine-tuned object detection, TL-OD, domain-adapted object detection	Fine-tuned CNN, CNN fine-tuning, CNN transfer learning with fine-tuning, adapted convolutional network
Apparentées	3	5
Résumé	Transfer learning with object detection starts from a deep neural network pretrained on a large image dataset — typically ImageNet for the backbone or COCO for the full detector — and adapts it to detect objects in a new domain. By reusing learned visual representations, it achieves strong detection accuracy with far fewer annotated images than training from scratch would require.	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.