Prune-and-Merge：免训练扩展 Vision Transformer 的方法
Prune-and-Merge: Training-Free Scaling of Vision Transformers
AI 导读
论文提出 Prune-and-Merge ViT，一个面向现成模型的免训练 token 削减框架，结合基于类别注意力的剪枝与基于相似度的合并来降低 ViT 的冗余计算。
正文 · 原文
Abstract:Vision Transformers achieve strong performance but incur high computational costs from quadratic token interactions. Training-free token reduction methods improve efficiency, but their robustness remains underexplored. We propose Prune-and Merge ViT, a training-free framework for off-the-shelf models. It combines class attention-based pruning with similarity-based merging to reduce redundancy while preserving semantic information. To evaluate robustness we introduce two metrics. Relative Accuracy Drop (RAD) measures relative accuracy degradation under transformations, and Prediction Flip Rate (PFR) quantifies prediction consistency. On pretrained ViT and DeiT, Prune-and-Merge reduces computation competitively while maintaining robustness and better accuracy than existing token reduction methods. Our analysis suggests that hybrid token reduction does not introduce hallucination-like behavior and preserves prediction stability for common image transformations.
| Comments: | Accepted at the GlobalSouthAI Workshop at NeurIPS 2026; 12 pages |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.18039 [cs.CV] |
| (or arXiv:2610.18039v3 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18039 arXiv-issued DOI via DataCite |
Submission history
From: Vatsal Singhal [view email]
[v1]
Tue, 13 Oct 2026 09:29:25 UTC (22 KB)
[v2]
Wed, 14 Oct 2026 04:42:32 UTC (22 KB)
[v3]
Tue, 10 Nov 2026 15:02:36 UTC (22 KB)
来源：arXiv cs.AI · arxiv.org