ScopeViT: Scale-Aware Vision Transformer

Open Webpage

Xuesong Nie, Haoyuan Jin, Yunfeng Yan, Xi Chen, Zhihang Zhu, Donglian Qi

Published: 2024, Last Modified: 25 Mar 2026Pattern Recognit. 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•ScopeViT: a general vision transformer for multi-scale visual interactions.•Scale-aware attention module enriches understanding across spatial scales.•Extensive experiments show the superiority of ScopeViT on various visual tasks.