元学习的多域学习:通过内循环学习在多域损失场景中采取最佳步骤
Multi-Domain Learning by Meta-Learning: Taking Optimal Steps in Multi-Domain Loss Landscapes by Inner-Loop Learning
摘要:
我们考虑一个模型不可知的解决方案的问题的多域学习(MDL)的多模态应用程序。许多现有的MDL技术是依赖于模型的解决方案,明确要求非平凡的架构变化,以构建特定领域的模块。因此,将这些MDL技术适当地应用于具有良好建立的模型的新问题,例如,用于语义分割的U-Net,可能需要各种低级实现工作。在本文中,给定新兴的多模态数据(例如,各种结构神经成像模式),我们的目标是使MDL纯粹的算法,使广泛使用的神经网络可以平凡地实现MDL的模型无关的方式。为此,我们考虑一个加权损失函数,并将其扩展到一个有效的程序,通过采用技术,从最近活跃的区域学习学习(元学习)。具体来说,我们采取内循环梯度步骤来动态估计损失函数超参数的后验分布。因此,我们的方法是模型不可知的,不需要额外的模型参数和网络架构的变化,相反,只需要一些有效的算法修改,以提高MDL的性能。我们展示了我们的解决方案,在医学成像中的拟合问题,特别是在白质高信号(WMH)的自动分割。我们看看两个神经成像模式(T1-MR和FLAIR)与互补的信息适合我们的问题。
英文摘要:
We consider a model-agnostic solution to the problem of Multi-Domain Learning (MDL) for multi-modal applications. Many existing MDL techniques are model-dependent solutions which explicitly require nontrivial architectural changes to construct domain-specific modules. Thus, properly applying these MDL techniques for new problems with well-established models, e.g. U-Net for semantic segmentation, may demand various low-level implementation efforts. In this paper, given emerging multi-modal data (e.g., various structural neuroimaging modalities), we aim to enable MDL purely algorithmically so that widely used neural networks can trivially achieve MDL in a model-independent manner. To this end, we consider a weighted loss function and extend it to an effective procedure by employing techniques from the recently active area of learning-to-learn (meta-learning). Specifically, we take inner-loop gradient steps to dynamically estimate posterior distributions over the hyperparameters of our loss function. Thus, our method is model-agnostic, requiring no additional model parameters and no network architecture changes; instead, only a few efficient algorithmic modifications are needed to improve performance in MDL. We demonstrate our solution to a fitting problem in medical imaging, specifically, in the automatic segmentation of white matter hyperintensity (WMH). We look at two neuroimaging modalities (T1-MR and FLAIR) with complementary information fitting for our problem.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。