论文标题
基于代理的深度度量学习的非偶然正规化
Non-isotropy Regularization for Proxy-based Deep Metric Learning
论文作者
论文摘要
深度度量学习（DML）的目的是学习可以简单地通过预定义的距离指标来表达语义关系的表示空间。最佳性能方法通常利用类代理作为样本替补，以更好地收敛和概括。但是，这些代理方法仅针对样品 - 螺旋距离进行优化。考虑到使用距离功能的固有非主体性，这可以诱导局部各向同性的样本分布，从而导致由于解决局部结构和样本之间的类内关系而导致的关键语义上下文。为了减轻这个问题，我们建议用于基于代理的深度度量学习的非异端正则化（$ \ MATHBB {NIR} $）。通过利用归一化的流，我们可以从各自的类代理中实现样本的独特翻译性。这使我们能够明确诱导代理周围的样品的非等于分布，以优化。在此过程中，我们为基于代理的目标提供了更好的学习本地结构。广泛的实验突出了$ \ Mathbb {Nir} $的一致概括益处，同时在标准基准CUB200-2011，CARS196和Stanford Online Products上实现竞争性和最先进的性能。此外，我们发现基于代理方法的优越融合属性仍然可以保留甚至改进，从而使$ \ mathbb {nir} $对实际用法非常有吸引力。可在https://github.com/explainableml/nonisotropicproxydml上获得代码。
Deep Metric Learning (DML) aims to learn representation spaces on which semantic relations can simply be expressed through predefined distance metrics. Best performing approaches commonly leverage class proxies as sample stand-ins for better convergence and generalization. However, these proxy-methods solely optimize for sample-proxy distances. Given the inherent non-bijectiveness of used distance functions, this can induce locally isotropic sample distributions, leading to crucial semantic context being missed due to difficulties resolving local structures and intraclass relations between samples. To alleviate this problem, we propose non-isotropy regularization ($\mathbb{NIR}$) for proxy-based Deep Metric Learning. By leveraging Normalizing Flows, we enforce unique translatability of samples from their respective class proxies. This allows us to explicitly induce a non-isotropic distribution of samples around a proxy to optimize for. In doing so, we equip proxy-based objectives to better learn local structures. Extensive experiments highlight consistent generalization benefits of $\mathbb{NIR}$ while achieving competitive and state-of-the-art performance on the standard benchmarks CUB200-2011, Cars196 and Stanford Online Products. In addition, we find the superior convergence properties of proxy-based methods to still be retained or even improved, making $\mathbb{NIR}$ very attractive for practical usage. Code available at https://github.com/ExplainableML/NonIsotropicProxyDML.
