硬件感知的函数型Kolmogorov-Arnold网络用于高效医学图像增强与分割
Hardware-Aware Functional Kolmogorov-Arnold Networks for Efficient Medical Image Enhancement and Segmentation
浏览论文内容
中文总结 AI 辅助
提出FunKANLite，通过两阶段硬件感知压缩和蒸馏，大幅减少FunKAN的参数与计算量，在保持分割和增强精度的同时，显著降低边缘设备能耗并提升吞吐量。
中文摘要 AI 辅助
函数型Kolmogorov-Arnold网络（FunKAN）在MRI吉布斯伪影去除和解剖分割方面达到了最先进的精度，但其11.6M参数和8.7 GFLOPs的计算量对于边缘医疗设备而言过于庞大。我们提出了FunKANLite，一种针对即时护理应用的两阶段、硬件感知的FunKAN压缩方法。FunKANLite-TR减少了空间先验，并将ResBlock偏移预测器替换为深度可分离块。其参数比FunKAN少1.9倍，且精度无损失。随后，我们将FunKANLite-TR蒸馏为FunKANLite-ST，后者降低了Hermite基的秩，将空间先验分解为低秩形式，并将滤波器宽度减半。FunKANLite-ST的参数比FunKAN少5.6倍，GFLOPs少3.7倍。在BUSI、GlaS和CVC-ClinicDB上，其IoU与FunKAN的差距保持在1.4个百分点以内，并在IXI上达到33.95 dB的PSNR。在NVIDIA Jetson Orin Nano和Raspberry Pi 5上，FunKANLite-ST将每次推理的能耗降低高达68%，并将吞吐量提高2.9倍。
英文摘要
Functional Kolmogorov-Arnold Networks (FunKAN) achieve state-of-the-art accuracy on MRI Gibbs artifact removal and anatomical segmentation, but their 11.6 M parameters and 8.7 GFLOPs are too large for edge medical devices. We present FunKANLite, a two-stage, hardware-aware compression of FunKAN for point-of-care use. FunKANLite-TR reduces the spatial prior and replaces the ResBlock offset predictor with a depthwise-separable block. It has 1.9x fewer parameters than FunKAN and no loss in accuracy. We then distill FunKANLite-TR into FunKANLite-ST, which lowers the Hermite basis rank, factorizes the spatial prior into a low-rank form, and halves the filter widths. FunKANLite-ST has 5.6x fewer parameters and 3.7x fewer GFLOPs than FunKAN. It stays within 1.4 percentage points IoU of FunKAN on BUSI, GlaS, and CVC-ClinicDB, and reaches 33.95 dB PSNR on IXI. On an NVIDIA Jetson Orin Nano and a Raspberry Pi 5, FunKANLite-ST reduces energy per inference by up to 68% and raises throughput by 2.9x.
发表机构
- University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）
机构由 AI 辅助整理，请以论文原文为准。
