Porównaj metody
Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.
| Osadzenia BERT× | Vision Transformer× | |
|---|---|---|
| Dziedzina≠ | Eksploracja tekstu | Uczenie głębokie |
| Rodzina≠ | Process / pipeline | Machine learning |
| Rok powstania≠ | 2019 | 2021 |
| Twórca≠ | Devlin, Chang, Lee & Toutanova (Google AI) | Dosovitskiy, A. et al. |
| Typ≠ | Contextual transformer text-representation method | Transformer architecture for images (self-attention over patches) |
| Źródło pierwotne≠ | Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186. DOI ↗ | Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗ |
| Inne nazwy≠ | contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri | Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images |
| Pokrewne≠ | 4 | 5 |
| Podsumowanie≠ | BERT-based text embeddings, introduced by Devlin and colleagues at Google AI in 2019, turn text into context-sensitive dense vectors using a bidirectional Transformer encoder. Because the meaning of a word shifts with its context, BERT produces richer representations than static methods such as Word2Vec or topic models like LDA. | The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs). |
| ScholarGateZbiór danych ↗ |
|
|