多模态胸部X射线分类器中的逐层门控提示截断
Layer-Wise Gate-Controlled Prompt Truncation in a Multimodal Chest X-Ray Classifier
- Central South University（中南大学）
- Hong Kong Baptist University（香港浸会大学）
- University of Minnesota（明尼苏达大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究在胸部X射线分类中提出逐层门控提示截断，通过预测保留比率缩短视觉提示，达到0.8996准确率，略优于固定长度基线，但未证实加速或临床优势。
AI中文摘要：
提示专家混合（MoPE）通过输入相关的提示组合来适配多模态变换器，同时保持固定的提示长度。我们在一个二分类胸部X射线分类试点研究中探讨了逐层门控扩展。控制器为每个样本预测一个保留比率，在小批量内平均这些比率，并使用得到的整数长度来截断静态和混合视觉提示。保留的混合提示也按各个比率进行缩放。在每种配置的一次记录运行中，门控模型达到了0.8996的最佳验证准确率，而固定长度基线为0.8969；相应的最终值分别为0.8963和0.8802。导出的门控统计量表明，在所有记录的训练点上，相对于配置的最大长度6，保留长度为1。这将完整的视觉序列从210个标记减少到200个标记，但没有直接的运行时测量证实加速优势。报告衍生的标签、报告文本作为输入、顺序数据划分以及缺乏重复的对照实验限制了结果的解释。研究结果记录了在配置的门控惩罚下提示的缩短；但并未确立样本特定的长度分配、相对于固定短提示的优越性或临床实用性。代码可在以下网址获取：此HTTPS URL。
英文摘要：
Mixture of Prompt Experts (MoPE) adapts multimodal transformers through input-dependent prompt composition, while retaining a fixed prompt length. We investigate a layer-wise gating extension in a binary chest X-ray classification pilot study. The controller predicts a retention ratio for each sample, averages these ratios within a mini-batch, and uses the resulting integer length to truncate the static and mixed visual prompts. Retained mixed prompts are also scaled by the individual ratios. In one recorded run per configuration, the gated model reached a best validation accuracy of 0.8996, compared with 0.8969 for the fixed-length baseline; the corresponding final values were 0.8963 and 0.8802. The exported gate statistics imply a retained length of one at all recorded training points, relative to a configured maximum of six. This reduces the complete visual sequence from 210 to 200 tokens, but no direct runtime measurements establish an acceleration benefit. Report-derived labels, report text as input, sequential data partitioning, and the absence of repeated controlled experiments limit interpretation. The findings document prompt shortening under the configured gate penalty; they do not establish sample-specific length allocation, superiority over fixed short prompts, or clinical utility. Code is available at: https://github.com/jingtaolei/mope-dynamic-prompt-truncation.
