Methoden vergleichen

	Feinabgestimmte Bildklassifikation	Feinabgestimmter Vision Transformer
Fachgebiet	Deep Learning	Deep Learning
Familie	Machine learning	Machine learning
Entstehungsjahr	2010–2014	2020-2021
Urheber	Yosinski, J. et al.; Pan, S. J. & Yang, Q.	Dosovitskiy, A. et al. (Google Brain)
Typ	Transfer learning / fine-tuning	Transfer learning / fine-tuning of attention-based image model
Wegweisende Quelle	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.	Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations (ICLR 2021).
Aliasnamen	fine-tuning for image recognition, transfer learning image classifier, pretrained CNN fine-tuning, domain-specific image classifier	Fine-Tuned ViT, ViT fine-tuning, Vision Transformer transfer learning, ViT downstream adaptation
Verwandt	5	5
Zusammenfassung	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-Tuned Vision Transformer adapts a large pre-trained ViT model — which splits images into fixed-size patches and processes them through self-attention layers — to a new image classification or recognition task using a relatively small labeled dataset. It achieves state-of-the-art accuracy in computer vision by leveraging rich representations learned during large-scale pre-training.