轻量级多尺度模型，用少参数实现高精度医学图像分割
Wave-GMS: Lightweight Multi-Scale Generative Model for Medical Image Segmentation
- 基于小波变换设计轻量化多尺度生成架构
- 仅需约260万参数，在4个数据集上达顶尖性能
- 适合资源受限的医院部署，支持大批次训练
为实现人工智能工具在医院和医疗设施中的公平部署，需要高性能且可在低成本GPU上训练的分割网络。本文提出Wave-GMS，一种轻量高效的医学图像分割多尺度生成模型。该模型参数量极小，无需加载内存密集型预训练视觉基础模型，并可在显存有限的GPU上支持大批次训练。我们在四个公开数据集（BUS、BUSI、Kvasir-Instrument、HAM10000）上进行了广泛实验，结果表明Wave-GMS在跨域泛化能力上表现优异，达到当前最优分割性能，同时仅需约260万可训练参数。代码已开源：https://github.com/ATPLab-LUMS/Wave-GMS。
原文摘要 · Abstract (English)
For equitable deployment of AI tools in hospitals and healthcare facilities, we need Deep Segmentation Networks that offer high performance and can be trained on cost-effective GPUs with limited memory and large batch sizes. In this work, we propose Wave-GMS, a lightweight and efficient multi-scale generative model for medical image segmentation. Wave-GMS has a substantially smaller number of trainable parameters, does not require loading memory-intensive pretrained vision foundation models, and supports training with large batch sizes on GPUs with limited memory. We conducted extensive experiments on four publicly available datasets (BUS, BUSI, Kvasir-Instrument, and HAM10000), demonstrating that Wave-GMS achieves state-of-the-art segmentation performance with superior cross-domain generalizability, while requiring only ~2.6M trainable parameters. Code is available at https://github.com/ATPLab-LUMS/Wave-GMS.
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。