Σύγκριση μεθόδων
Εξετάστε τις επιλεγμένες μεθόδους δίπλα-δίπλα· οι γραμμές που διαφέρουν επισημαίνονται.
| Επιβλεπόμενος Μετασχηματιστής Όρασης (Semi-supervised Vision Transformer)× | Ημι-επιβλεπόμενη Ταξινόμηση Βασισμένη σε BERT× | |
|---|---|---|
| Πεδίο | Βαθιά Μάθηση | Βαθιά Μάθηση |
| Οικογένεια | Machine learning | Machine learning |
| Έτος προέλευσης≠ | 2021–2022 | 2019–2020 |
| Δημιουργός≠ | Dosovitskiy et al. (ViT); semi-supervised extensions by multiple groups (2021–2023) | Multiple groups (Xie et al.; Chen et al.; Devlin et al. for BERT base) |
| Τύπος≠ | Semi-supervised deep learning for image understanding | Semi-supervised fine-tuning of pre-trained transformer |
| Θεμελιώδης πηγή≠ | 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 ↗ | Xie, Q., Dai, Z., Hovy, E., Luong, T., & Le, Q. (2020). Unsupervised Data Augmentation for Consistency Training. Advances in Neural Information Processing Systems (NeurIPS), 33, 27780–27792. link ↗ |
| Εναλλακτικές ονομασίες | Semi-supervised ViT, SSL-ViT, Semi-supervised Patch-based Transformer, Semi-supervised Self-Attention Image Model | Semi-supervised BERT, BERT SSL Classification, BERT with Unlabeled Data, BERT Semi-supervised Fine-tuning |
| Συναφείς | 6 | 6 |
| Σύνοψη≠ | 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. | Semi-supervised BERT-based classification fine-tunes a pre-trained BERT encoder on a small pool of labeled text examples while simultaneously leveraging a much larger body of unlabeled text — via consistency training, pseudo-labeling, or data augmentation — to produce high-quality classifiers even when manual annotation is scarce. |
| ScholarGateΣύνολο δεδομένων ↗ |
|
|