提出TauFlow模型，让轻量级医学图像分割更准更快。
TauFlow: Dynamic Causal Constraint for Complexity-Adaptive Lightweight Segmentation
- 用类脑机制动态调节特征更新速度，区分背景与病灶边界。
- 参数少于0.5M时准确率仍高，特征冲突率从35%-40%降至8%-10%。
- 适合部署在边缘设备的轻量级医学图像分割任务。
在边缘设备上部署轻量级医学图像分割模型面临两大挑战：一是有效处理病灶边界与背景区域之间的显著差异；二是极端轻量化设计（如参数少于0.5M）导致准确率急剧下降。为此，本文提出TauFlow，一种新型轻量级分割模型。其核心是受类脑机制启发的动态特征响应策略，包含两项关键创新：卷积长时常数单元（ConvLTC），可动态调节特征更新速率，对低频背景“慢处理”，对高频边界“快响应”；以及基于脉冲时间依赖可塑性（STDP）的自组织模块，显著缓解编码器与解码器间的特征冲突，将冲突率从约35%-40%降低至8%-10%。
原文摘要 · Abstract (English)
Deploying lightweight medical image segmentation models on edge devices presents two major challenges: 1) efficiently handling the stark contrast between lesion boundaries and background regions, and 2) the sharp drop in accuracy that occurs when pursuing extremely lightweight designs (e.g., <0.5M parameters). To address these problems, this paper proposes TauFlow, a novel lightweight segmentation model. The core of TauFlow is a dynamic feature response strategy inspired by brain-like mechanisms. This is achieved through two key innovations: the Convolutional Long-Time Constant Cell (ConvLTC), which dynamically regulates the feature update rate to "slowly" process low-frequency backgrounds and "quickly" respond to high-frequency boundaries; and the STDP Self-Organizing Module, which significantly mitigates feature conflicts between the encoder and decoder, reducing the conflict rate from approximately 35%-40% to 8%-10%.
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。