提出轻量级优化器，大幅降低大图像配准内存占用
Factored Levenberg-Marquardt for Diffeomorphic Image Registration: An efficient optimizer for FireANTs
- 用单标量参数替代Adam的多状态，实现低内存优化
- 大体积图像内存减少24.6%，在四个数据集上性能不降
- 仅调一个超参即可跨模态适配，适合医疗影像大图配准
FireANTs引入了一种新型欧拉下降方法，可与任意优化器兼容，用于测试时优化的微分图像配准，具备GPU加速实现。其默认使用Adam优化器以实现快速稳健的优化，但Adam需存储动量和平方动量等状态变量，内存开销大，难以处理大尺寸图像。本文提出一种改进的Levenberg-Marquardt（LM）优化器，仅需一个标量阻尼参数作为状态，并通过信赖域方法自适应调整。该优化器在大体积图像上内存消耗降低最多达24.6%，同时在全部四个数据集上保持性能。仅在一个脑部MRI数据集上调好的单一超参数配置，无需修改即可成功应用于肺部CT及跨模态腹部配准，在三个数据集上表现匹配或超越Adam。此外，我们还对采用类似Metropolis-Hastings的拒绝步骤以防止损失函数恶化更新的效果进行了消融研究。
原文摘要 · Abstract (English)
FireANTs introduced a novel Eulerian descent method for plug-and-play behavior with arbitrary optimizers adapted for diffeomorphic image registration as a test-time optimization problem, with a GPU-accelerated implementation. FireANTs uses Adam as its default optimizer for fast and more robust optimization. However, Adam requires storing state variables (i.e. momentum and squared-momentum estimates), each of which can consume significant memory, prohibiting its use for significantly large images. In this work, we propose a modified Levenberg-Marquardt (LM) optimizer that requires only a single scalar damping parameter as optimizer state, that is adaptively tuned using a trust region approach. The resulting optimizer reduces memory by up to 24.6% for large volumes, and retaining performance across all four datasets. A single hyperparameter configuration tuned on brain MRI transfers without modification to lung CT and cross-modal abdominal registration, matching or outperforming Adam on three of four benchmarks. We also perform ablations on the effectiveness of using Metropolis-Hastings style rejection step to prevent updates that worsen the loss function.
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。