Compara mètodes
Revisa els mètodes seleccionats l'un al costat de l'altre; les files que difereixen es ressalten.
| Vision Transformer Semisupervisat× | Vision Transformer ajustat (Fine-Tuned Vision Transformer)× | |
|---|---|---|
| Camp | Aprenentatge profund | Aprenentatge profund |
| Família | Machine learning | Machine learning |
| Any d'origen≠ | 2021–2022 | 2020-2021 |
| Autor original≠ | Dosovitskiy et al. (ViT); semi-supervised extensions by multiple groups (2021–2023) | Dosovitskiy, A. et al. (Google Brain) |
| Tipus≠ | Semi-supervised deep learning for image understanding | Transfer learning / fine-tuning of attention-based image model |
| Font seminal≠ | 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. International Conference on Learning Representations (ICLR 2021). link ↗ | 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). link ↗ |
| Àlies | Semi-supervised ViT, SSL-ViT, Semi-supervised Patch-based Transformer, Semi-supervised Self-Attention Image Model | Fine-Tuned ViT, ViT fine-tuning, Vision Transformer transfer learning, ViT downstream adaptation |
| Relacionats≠ | 6 | 5 |
| Resum≠ | Semi-supervised Vision Transformer applies the patch-based self-attention architecture of ViT to settings where only a fraction of images are labeled, exploiting large unlabeled corpora through pseudo-labeling, consistency regularization, or self-supervised pretext tasks before fine-tuning on the small labeled set. This approach achieves near-supervised accuracy even when labeled images are scarce. | 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. |
| ScholarGateConjunt de dades ↗ |
|
|