用提示引导动态剪枝，让医学图像分割更高效
Prompt-based Dynamic Token Pruning for Efficient Segmentation of Medical Images
- 基于提示的注意力机制排序令牌，筛选关键区域
- 令牌量减少35%-55%，推理速度提升且精度不变
- 适合资源受限场景下的实时医学图像分析
视觉变换器（ViT）在处理大量令牌时计算开销高，限制了其在医学图像分析中的应用。本文提出一种提示驱动的自适应令牌剪枝方法（PrATo），通过提示提供的空间先验对令牌相关性进行排序，低相关性令牌被降权，仅关键令牌传递至后续阶段。该数据驱动策略在不牺牲分割精度的前提下，显著提升推理速度并降低计算成本。实验表明，令牌数量减少约35%-55%，相较于基线模型大幅降低计算开销。所提框架可集成于多种先进模型，推动低成本医学图像处理，在资源受限环境中实现高效实时诊断。
原文摘要 · Abstract (English)
The high computational demands of Vision Transformers (ViTs) in processing a large number of tokens often constrain their practical application in analyzing medical images. This research proposes a Prompt-driven Adaptive Token ({\it PrATo}) pruning method to selectively reduce the processing of irrelevant tokens in the segmentation pipeline. The prompt-based spatial prior helps to rank the tokens according to their relevance. Tokens with low-relevance scores are down-weighted, ensuring that only the relevant ones are propagated for processing across subsequent stages. This data-driven pruning strategy improves segmentation accuracy and inference speed by allocating computational resources to essential regions. The proposed framework is integrated with several state-of-the-art models to facilitate the elimination of irrelevant tokens, thereby enhancing computational efficiency while preserving segmentation accuracy. The experimental results show a reduction of $\sim$ 35-55% tokens; thus reducing the computational costs relative to baselines. Cost-effective medical image processing, using our framework, facilitates real-time diagnosis by expanding its applicability in resource-constrained environments.
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。