Porównaj metody
Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.
| Mamba Wizyjny× | Swin Transformer× | |
|---|---|---|
| Dziedzina | Uczenie głębokie | Uczenie głębokie |
| Rodzina | Machine learning | Machine learning |
| Rok powstania≠ | 2024 | 2021 |
| Twórca≠ | Li Zhu | Ze Liu |
| Typ | Neural network architecture | Neural network architecture |
| Źródło pierwotne≠ | Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., & Wang, X. (2024). Vision Mamba: Efficient state space models for image understanding. In International Conference on Machine Learning. link ↗ | Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin Transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 10012-10022). DOI ↗ |
| Inne nazwy | ViM, Mamba for Vision | Swin, Hierarchical Vision Transformer |
| Pokrewne | 4 | 4 |
| Podsumowanie≠ | Vision Mamba is an efficient state space model approach for image understanding introduced in 2024 that adapts Mamba, a linear-complexity sequence model, to computer vision. By reformulating image tokens as sequences and using state space models, Vision Mamba achieves competitive accuracy with transformers while maintaining linear computational complexity. | The Swin Transformer is a hierarchical vision transformer introduced by Liu et al. in 2021 that uses shifted window attention to achieve computational efficiency while maintaining strong performance on computer vision tasks. Unlike the original Vision Transformer which applies global self-attention, Swin uses local window-based attention with periodic shifting to balance expressiveness and efficiency. |
| ScholarGateZbiór danych ↗ |
|
|