Swin Transformer
Swin Transformer ni transformer ya maono yenye ngazi iliyoanzishwa na Liu et al. mwaka 2021 ambayo hutumia usikivu wa dirisha lililohamishwa ili kufikia ufanisi wa kompyuta huku ikidumisha utendaji kazi wenye nguvu katika kazi za maono ya kompyuta. Tofauti na Vision Transformer ya awali ambayo hutumia usikivu wa jumla, Swin hutumia usikivu wa msingi wa dirisha na uhamishaji wa mara kwa mara ili kusawazisha uhamishaji na ufanisi.
Soma mbinu kamili
Ingia kwa akaunti ya bure ili kusoma sehemu hii.
Method map
The neighbourhood of related methods — select a node to explore.
Vyanzo
- 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: 10.1109/ICCV48922.2021.00986 ↗
Jinsi ya kunukuu ukurasa huu
ScholarGate. (2026, June 3). Shifted Window Transformer for Vision. ScholarGate. https://scholargate.app/sw/deep-learning/swin-transformer
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- DETR (Detection Transformer)Ujifunzaji wa Kina↔ compare
- Autoenkoda ZilizofunikwaUjifunzaji wa Kina↔ compare
- Vision MambaUjifunzaji wa Kina↔ compare
- Transformer wa MaonoUjifunzaji wa Kina↔ compare
Imerejelewa na
Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →