# Vote&Mix: Plug-and-Play Token Reduction for Efficient Vision Transformer Source: [Vote&Mix: Plug-and-Play Token Reduction for Efficient Vision Transformer]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:39:01.541Z Authors: Shuai Peng, Di Fu, Baole Wei, Yong Cao, Liangcai Gao, Zhi Tang Published: 2024-08-30T07:48:05.000Z ## Abstract Despite the remarkable success of Vision Transformers (ViTs) in various visual tasks, they are often hindered by substantial computational cost. In this work, we introduce Vote\\&Mix (\\textbf{VoMix}), a plug-and-play and parameter-free token reduction method, which can be readily applied to off-the-shelf ViT models \\textit{without any training}. VoMix tackles the computational redundancy of ViTs by identifying tokens with high homogeneity through a layer-wise token similarity voting mechanism. Subsequently, the selected tokens are mixed into the retained set, thereby preserving visual information. Experiments demonstrate VoMix significantly improves the speed-accuracy tradeoff of ViTs on both images and videos. Without any training, VoMix achieves a 2$\\times$ increase in throughput of existing ViT-H on ImageNet-1K and a 2.4$\\times$ increase in throughput of existing ViT-L on Kinetics-400 video dataset, with a mere 0.3\\% drop in top-1 accuracy. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()