Abstract: Aiming at the challenges of Vision Transformer (ViT) model in terms of computational cost, an adaptive pruning strategy for tokens based on Closeness-Centrality is innovatively proposed. The ...
一些您可能无法访问的结果已被隐去。
显示无法访问的结果一些您可能无法访问的结果已被隐去。
显示无法访问的结果