联合分布问题：用于Few-Shot分类的深布朗距离协方差
Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification
摘要：
Few-Shot分类是一个具有挑战性的问题，因为每个新任务只给出很少的训练样本。解决这一挑战的有效研究路线之一集中在学习由查询图像和某类的少数支持图像之间的相似性度量驱动的深度表示。从统计学上讲，这相当于测量图像特征的依赖性，这些特征被视为高维嵌入空间中的随机向量。以前的方法要么只使用边缘分布，而不考虑联合分布，遭受有限的表示能力，或计算昂贵，虽然利用联合分布。在本文中，我们提出了一种深度布朗距离协方差（DeepBDC）方法的Few-Shot分类。DeepBDC的中心思想是通过测量嵌入特征的联合特征函数与边缘值的乘积之间的差异来学习图像表示。由于BDC度量是解耦的，我们将其制定为高度模块化和高效的层。此外，我们在两个不同的Few-Shot分类框架中实例化DeepBDC。我们在六个标准的Few-Shot图像基准上进行了实验，涵盖了一般目标识别，细粒度分类和跨域分类。广泛的评估表明，我们的DeepBDC显著优于同行，同时建立了新的最先进的结果。源代码可在http://www.peihuali.org/DeepBDC上获得
英文摘要：
Few-shot classification is a challenging problem as only very few training examples are given for each new task. One of the effective research lines to address this challenge focuses on learning deep representations driven by a similarity measure between a query image and few support images of some class. Statistically, this amounts to measure the dependency of image features, viewed as random vectors in a high-dimensional embedding space. Previous methods either only use marginal distributions without considering joint distributions, suffering from limited representation capability, or are computationally expensive though harnessing joint distributions. In this paper, we propose a deep Brownian Distance Covariance (DeepBDC) method for few-shot classification. The central idea of DeepBDC is to learn image representations by measuring the discrepancy between joint characteristic functions of embedded features and product of the marginals. As the BDC metric is decoupled, we formulate it as a highly modular and efficient layer. Furthermore, we instantiate DeepBDC in two different few-shot classification frameworks. We make experiments on six standard few-shot image benchmarks, covering general object recognition, fine-grained categorization and cross-domain classification. Extensive evaluations show our DeepBDC significantly outperforms the counterparts, while establishing new state-of-the-art results. The source code is available at http://www.peihuali.org/DeepBDC
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。
