评估视觉Transformer在小麦表型中的合并容忍度，发现分类任务最鲁棒，检测与分割受限于结构细节。
How Merge-Tolerant Are Vision Transformers for Wheat Phenotyping?
- 使用无训练令牌合并技术优化ViT推理效率
- 分类任务合并后精度下降<3%，检测/分割下降超15%
- 适合边缘部署场景下的模型压缩研究者参考
基于视觉的小麦表型分析需在部署限制下进行重复测量，涵盖生育期识别、穗数计数和器官分割。标准视觉变换器（ViTs）虽通用，但二次注意力机制限制了高通量与边缘推理。无训练令牌合并因其可直接插入已训练模型而具吸引力。本文系统评估了ToMe与互对合并方法在生育期分类、穗检测与器官分割任务中的表现，衡量任务质量、吞吐量、令牌数量及峰值GPU内存，并额外在Raspberry Pi 5上测试。结果揭示明确层级：分类任务高度容忍合并，而检测与分割受重复实例、细长器官、密集边界、重建需求及运行时开销制约。优化的注意力后端可能抵消表面加速，因此部署价值必须在目标运行时环境中实测，而非仅凭令牌数推断。
原文摘要 · Abstract (English)
Vision-based wheat phenotyping requires repeated measurements under deployment constraints, from growth-stage recognition to wheat-head counting and organ segmentation. Plain Vision Transformers (ViTs) provide a common architecture for these tasks, but quadratic attention limits high-throughput and edge inference. Training-free token merging is attractive because it can be inserted into trained models without retraining. We provide a systematic benchmark of ToMe and Mutual Pair Merging across growth-stage classification, wheat-head detection, and wheat-organ segmentation, measuring task quality, throughput, token count, and peak GPU memory, with additional Raspberry Pi 5 measurements. The benchmark reveals a clear hierarchy: classification is highly merge-tolerant, while detection and segmentation are constrained by repeated instances, thin organs, dense boundaries, reconstruction, and runtime overhead. Optimized attention backends can erase apparent speedups, so deployment value must be profiled on the target runtime rather than inferred from token count.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。