Sammenlign metoder
Gjennomgå de valgte metodene side om side; rader som avviker, er uthevet.
| Oppmerksomhetsmekanisme× | Vision Transformer× | |
|---|---|---|
| Fagfelt | Dyp læring | Dyp læring |
| Familie | Machine learning | Machine learning |
| Opprinnelsesår≠ | 2015 | 2021 |
| Opphavsperson≠ | Bahdanau, D.; Luong, M.T. | Dosovitskiy, A. et al. |
| Type≠ | Neural attention layer (encoder-decoder) | Transformer architecture for images (self-attention over patches) |
| Opprinnelig kilde≠ | Bahdanau, D., Cho, K. & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. ICLR. link ↗ | Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗ |
| Alias≠ | Dikkat Mekanizması (Bahdanau / Luong Attention), dikkat mekanizmasi, neural attention, additive attention | Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images |
| Relaterte | 5 | 5 |
| Sammendrag≠ | The attention mechanism, introduced by Bahdanau, Cho and Bengio in 2015 and refined by Luong, Pham and Manning the same year, lets a sequence decoder dynamically learn which of the encoder's outputs to focus on at each step. Before the Transformer, it substantially improved machine-translation quality by freeing models from compressing an entire input into a single fixed vector. | 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). |
| ScholarGateDatasett ↗ |
|
|