類似資料

• SPoT: Subpixel Placement of Tokens in Vision Transformers
  著者:: Hjelkrem-Tan, Martine, 等
  出版事項: (2025)
• Why Prototypes Collapse: Diagnosing and Preventing Partial Collapse in Prototypical Self-Supervised Learning
  著者:: Arteaga, Gabriel Y., 等
  出版事項: (2025)
• Differentiable Hierarchical Visual Tokenization
  著者:: Aasan, Marius, 等
  出版事項: (2025)
• A Spitting Image: Modular Superpixel Tokenization in Vision Transformers
  著者:: Aasan, Marius, 等
  出版事項: (2024)
• Self-Organizing Visual Prototypes for Non-Parametric Representation Learning
  著者:: Silva, Thalles, 等
  出版事項: (2025)