AFIDAF: Alternating Fourier and Image Domain Adaptive Filters as an Efficient Alternative to Attention in ViTs

Documenti analoghi

• SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging
  di: Tran, Nhat Thanh, et al.
  Pubblicazione: (2025)
• CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs
  di: Ramachandran, Akshat, et al.
  Pubblicazione: (2024)
• Communication Efficient Split Learning of ViTs with Attention-based Double Compression
  di: Alvetreti, Federico, et al.
  Pubblicazione: (2025)
• Refining Datapath for Microscaling ViTs
  di: Xiao, Can, et al.
  Pubblicazione: (2025)
• Purrturbed but Stable: Human-Cat Invariant Representations Across CNNs, ViTs and Self-Supervised ViTs
  di: Shah, Arya, et al.
  Pubblicazione: (2025)