Jämför metoder
Granska de valda metoderna sida vid sida; rader som skiljer sig är markerade.
| Mamba (tillståndsrumsmodell)× | Vision Transformer× | |
|---|---|---|
| Ämnesområde | Djupinlärning | Djupinlärning |
| Familj | Machine learning | Machine learning |
| Ursprungsår≠ | 2023 | 2021 |
| Upphovsperson≠ | Albert Gu | Dosovitskiy, A. et al. |
| Typ≠ | Neural network architecture | Transformer architecture for images (self-attention over patches) |
| Ursprungskälla≠ | Gu, A., & Dao, C. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.08956. link ↗ | Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗ |
| Alias≠ | Mamba, State space models, Selective state space | Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images |
| Närliggande≠ | 4 | 5 |
| Sammanfattning≠ | Mamba is a sequence model architecture introduced by Gu and Dao in 2023 that achieves linear-time complexity while maintaining strong performance on language modeling tasks. By combining state space models with input-dependent selectivity, Mamba addresses the quadratic complexity of transformers while preserving modeling power. | 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). |
| ScholarGateDatamängd ↗ |
|
|