基于几何方法的少样本学习--基于遗传诱导的沃罗诺伊图
Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approach
摘要:
少样本学习(Few-Shot learning,FSL)是指从丰富的基本样本到不足的新样本的快速泛化过程。尽管近年来进行了广泛的研究,但FSL仍然无法为广泛的实际应用提供令人满意的解决方案。为了应对这一挑战,本文从几何的角度研究了FSL问题。一个观察是,广泛接受的ProtoNet模型本质上是特征空间中的沃罗诺伊图(VD)。我们利用计算几何的一个新进展,称为诱导的沃罗诺伊图(CIVD)的更新。从最简单的最近邻模型开始,CIVD逐渐融合了簇到点,然后簇到簇的关系进行空间细分,用于提高FSL多个阶段的准确性和鲁棒性。具体来说,我们使用CIVD(1)集成参数和非参数Few-Shot分类器;(2)结合特征表示和代理表示;(3)利用特征级,变换级和几何级的异质性来获得更好的集成。我们基于CIVD的工作流程使我们能够在mini-ImageNet、CUB和分层ImagenNet数据集上实现最先进的新结果,并在最佳基础上进行${\sim}2\%{-}5\%$改进。总之,CIVD提供了一个数学上优雅和几何上可解释的框架,可以补偿极端的数据不足,防止过拟合,并允许快速几何集成数千个单独的VD。这一切都让FSL变得更加强大。
英文摘要:
Few-shot learning (FSL) is the process of rapid generalization from abundant base samples to inadequate novel samples. Despite extensive research in recent years, FSL is still not yet able to generate satisfactory solutions for a wide range of real-world applications. To confront this challenge, we study the FSL problem from a geometric point of view in this paper. One observation is that the widely embraced ProtoNet model is essentially a Voronoi Diagram (VD) in the feature space. We retrofit it by making use of a recent advance in computational geometry called Cluster-induced Voronoi Diagram (CIVD). Starting from the simplest nearest neighbor model, CIVD gradually incorporates cluster-to-point and then cluster-to-cluster relationships for space subdivision, which is used to improve the accuracy and robustness at multiple stages of FSL. Specifically, we use CIVD (1) to integrate parametric and nonparametric few-shot classifiers; (2) to combine feature representation and surrogate representation; (3) and to leverage feature-level, transformation-level, and geometry-level heterogeneities for a better ensemble. Our CIVD-based workflow enables us to achieve new state-of-the-art results on mini-ImageNet, CUB, and tiered-ImagenNet datasets, with ${\sim}2\%{-}5\%$ improvements upon the next best. To summarize, CIVD provides a mathematically elegant and geometrically interpretable framework that compensates for extreme data insufficiency, prevents overfitting, and allows for fast geometric ensemble for thousands of individual VD. These together make FSL stronger.
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。