ICCV

SPoT: Subpixel Placement of Tokens in Vision Transformers

SPoT: 视觉变换器中令牌的子像素位置

Martine Hjelkrem-Tan, Marius Aasan, Gabriel Y. Arteaga, Adín Ramírez Rivera

AI总结 SPoT通过子像素位置策略提升视觉变换器的稀疏性利用，减少令牌数量以提高效率与准确性。

Comments Appeared in Workshop on Efficient Computing under Limited Resources: Visual Computing (ICCV 2025). Code available at https://github.com/dsb-ifi/SPoT