学习经验 Bregman 散度用于不确定距离表示（英文版）

英文标题：Learning Empirical Bregman Divergence for Uncertain Distance Representation中文摘要：本文介绍了如何通过深度学习，从数据中直接学习经验 Bregman 分歧，然后在五个公开数据集上展示了该方法的有效性，特别是在模式识别问题方面。英文摘要：Deep metric learning techniques have been used for visual representation invarious supervised and unsupervised learning tasks through learning embeddingsof samples with deep networks. However, classic approaches, which employ afixed distance metric as a similarity function between two embeddings, may leadto suboptimal performance for ca