Порівняння методів
Переглядайте обрані методи поруч; рядки з відмінностями підсвічено.
| BERT Embeddings× | Трансформер для комп'ютерного зору× | |
|---|---|---|
| Галузь≠ | Інтелектуальний аналіз тексту | Глибоке навчання |
| Родина≠ | Process / pipeline | Machine learning |
| Рік появи≠ | 2019 | 2021 |
| Автор методу≠ | Devlin, Chang, Lee & Toutanova (Google AI) | Dosovitskiy, A. et al. |
| Тип≠ | Contextual transformer text-representation method | Transformer architecture for images (self-attention over patches) |
| Основоположне джерело≠ | 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 ↗ |
| Інші назви≠ | contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri | Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images |
| Пов'язані≠ | 4 | 5 |
| Підсумок≠ | 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). |
| ScholarGateНабір даних ↗ |
|
|