Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Swin Transformer× | DETR (Detection Transformer)× | Vision Mamba× | |
|---|---|---|---|
| Obor | Hluboké učení | Hluboké učení | Hluboké učení |
| Rodina | Machine learning | Machine learning | Machine learning |
| Rok vzniku≠ | 2021 | 2020 | 2024 |
| Tvůrce≠ | Ze Liu | Nicolas Carion | Li Zhu |
| Typ | Neural network architecture | Neural network architecture | Neural network architecture |
| Původní zdroj≠ | 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 ↗ | Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. In European Conference on Computer Vision (pp. 213-229). Springer, Cham. DOI ↗ | 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 ↗ |
| Další názvy | Swin, Hierarchical Vision Transformer | Detection Transformer, DETR | ViM, Mamba for Vision |
| Příbuzné | 4 | 4 | 4 |
| Shrnutí≠ | 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. | DETR (Detection Transformer) is an end-to-end framework for object detection introduced by Carion et al. in 2020 that reformulates detection as a direct set prediction problem using transformers. Unlike traditional approaches that use hand-crafted post-processing like non-maximum suppression, DETR treats object detection as a sequence-to-sequence problem where the transformer predicts all objects at once. | 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. |
| ScholarGateDatová sada ↗ |
|
|
|