ScholarGate
Asistente

Comparar métodos

Revisa los métodos seleccionados uno junto a otro; las filas que difieren aparecen resaltadas.

Swin Transformer×Vision Transformer×
CampoAprendizaje profundoAprendizaje profundo
FamiliaMachine learningMachine learning
Año de origen20212021
Autor originalZe LiuDosovitskiy, A. et al.
TipoNeural network architectureTransformer architecture for images (self-attention over patches)
Fuente seminalLiu, 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 ↗Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗
AliasSwin, Hierarchical Vision TransformerGörsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Relacionados45
ResumenThe 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.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).
ScholarGateConjunto de datos
  1. v1
  2. 1 Fuentes
  3. PUBLISHED
  1. v1
  2. 2 Fuentes
  3. PUBLISHED

Ir a la búsqueda Descargar diapositivas

ScholarGateComparar métodos: Swin Transformer · Vision Transformer. Recuperado el 2026-06-18 de https://scholargate.app/es/compare