CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications

Documenti analoghi

• TPC-ViT: Token Propagation Controller for Efficient Vision Transformer
  di: Zhu, Wentao
  Pubblicazione: (2024)
• ACC-ViT : Atrous Convolution's Comeback in Vision Transformers
  di: Ibtehaz, Nabil, et al.
  Pubblicazione: (2024)
• EA-ViT: Efficient Adaptation for Elastic Vision Transformer
  di: Zhu, Chen, et al.
  Pubblicazione: (2025)
• ViT-1.58b: Mobile Vision Transformers in the 1-bit Era
  di: Yuan, Zhengqing, et al.
  Pubblicazione: (2024)
• ScalingGaussian: Enhancing 3D Content Creation with Generative Gaussian Splatting
  di: Chen, Shen, et al.
  Pubblicazione: (2024)