ScholarGate
Assistent

Methoden vergleichen

Prüfen Sie die ausgewählten Methoden nebeneinander; abweichende Zeilen sind hervorgehoben.

Swin Transformer×Masked Autoencoders×
FachgebietDeep LearningDeep Learning
FamilieMachine learningMachine learning
Entstehungsjahr20212021
UrheberZe LiuKaiming He
TypNeural network architectureNeural network architecture
Wegweisende QuelleLiu, 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 ↗He, K., Chen, X., Xie, S., Li, Y., Dollár, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 16000-16009). DOI ↗
AliasnamenSwin, Hierarchical Vision TransformerMAE, Vision MAE
Verwandt44
ZusammenfassungThe 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.Masked Autoencoders (MAE) is a self-supervised learning approach introduced by He et al. in 2021 that masks random patches of an image and trains a model to reconstruct the missing content. Adapting the masked language modeling paradigm from NLP to vision, MAE learns rich visual representations by solving a challenging reconstruction task without requiring labels.
ScholarGateDatensatz
  1. v1
  2. 1 Quellen
  3. PUBLISHED
  1. v1
  2. 1 Quellen
  3. PUBLISHED

Zur Suche Folien herunterladen

ScholarGateMethoden vergleichen: Swin Transformer · Masked Autoencoders. Abgerufen am 2026-06-18 von https://scholargate.app/de/compare