Сравнение на методи
Прегледайте избраните методи един до друг; редовете с разлики са откроени.
| Полу-наблюдаван Трансформър за Визия× | Трансформер за зрение със самообучение× | |
|---|---|---|
| Област | Дълбоко обучение | Дълбоко обучение |
| Семейство | Machine learning | Machine learning |
| Година на възникване | 2021–2022 | 2021–2022 |
| Създател≠ | Dosovitskiy et al. (ViT); semi-supervised extensions by multiple groups (2021–2023) | Caron et al. (DINO); He et al. (MAE) |
| Тип≠ | Semi-supervised deep learning for image understanding | Self-supervised pre-training for vision transformers |
| Основополагащ източник≠ | 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 ↗ | Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging Properties in Self-Supervised Vision Transformers. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 9650–9660. link ↗ |
| Други названия | Semi-supervised ViT, SSL-ViT, Semi-supervised Patch-based Transformer, Semi-supervised Self-Attention Image Model | SSL-ViT, self-supervised ViT, unsupervised ViT pre-training, vision transformer self-supervised pre-training |
| Свързани≠ | 6 | 4 |
| Резюме≠ | 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. | Self-supervised Vision Transformer (SSL-ViT) applies self-supervised pre-training objectives — such as masked patch prediction (MAE) or self-distillation with no labels (DINO) — to the Vision Transformer architecture, enabling powerful visual representations to be learned from large unlabeled image corpora before any task-specific fine-tuning. |
| ScholarGateНабор от данни ↗ |
|
|