Exploiting Information Redundancy in Attention Maps for Extreme Quantization of Vision Transformers

Documenti analoghi

• Where Do Tokens Go? Understanding Pruning Behaviors in STEP at High Resolutions
  di: Szczepanski, Michal, et al.
  Pubblicazione: (2025)
• Codebook-enabled Generative End-to-end Semantic Communication Powered by Transformer
  di: Ye, Peigen, et al.
  Pubblicazione: (2024)
• Dynamic Accumulated Attention Map for Interpreting Evolution of Decision-Making in Vision Transformer
  di: Liao, Yi, et al.
  Pubblicazione: (2025)
• Class-Discriminative Attention Maps for Vision Transformers
  di: Brocki, Lennart, et al.
  Pubblicazione: (2023)
• LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition
  di: Hu, Youbing, et al.
  Pubblicazione: (2024)