Pair-wise loss functions have been extensively studied and shown to continuously improve the performance of deep metric learning (DML). However, they are primarily designed with intuition based on simple toy examples, and experimentally identifying the truly effective design is difficult in complicated, real-world cases. In this paper, we provide a new methodology for systematically studying weighting strategies of various pair-wise loss functions, and rethink pair weighting with an embedding memory. We delve into the weighting mechanisms by decomposing the pair-wise functions, and study positive and negative weights separately using direct weight assignment. This allows us to study various weighting functions deeply and systematically via weight curves, and identify a number of meaningful, comprehensive and insightful facts, which come up with our key observation on memory-based DML: it is critical to mine hard negatives and discard easy negatives which are less informative and redundant, but weighting on positive pairs is not helpful. This results in an efficient but surprisingly simple rule to design the weighting scheme, making it significantly different from existing mini-batch based methods which design various sophisticated loss functions to weight pairs carefully. Finally, we conduct extensive experiments on three large-scale visual retrieval benchmarks, and demonstrate the superiority of memory-based DML over recent mini-batch based approaches, by using a simple contrastive loss with momentum-updated memory.

中文翻译：

---

重新思考具有嵌入记忆的深度对比学习

逐对损失函数已得到广泛研究，并显示出可以不断提高深度度量学习（DML）的性能。但是，它们主要是基于简单的玩具示例而凭直觉进行设计的，并且在复杂的实际案例中，很难通过实验确定真正有效的设计。在本文中，我们提供了一种新的方法，可以系统地研究各种成对损失函数的加权策略，并重新考虑具有嵌入式记忆的成对加权。我们通过分解成对函数来研究加权机制，并使用直接权重分配分别研究正负权重。这样一来，我们就可以通过权重曲线深入而系统地研究各种权重函数，并找出许多有意义，全面和有见地的事实，这是我们对基于内存的DML的主要观察结果：挖掘硬底片并丢弃信息量和冗余度较低的容易底片是至关重要的，但是对正对进行加权无济于事。这导致设计加权方案的有效但出乎意料的简单规则，使其与现有的基于小批量的方法显着不同，现有的基于小批量的方法精心设计了各种复杂的损失函数以加权对。最后，我们在三个大型视觉检索基准上进行了广泛的实验，并通过使用带有动量更新的内存的简单对比损失，证明了基于内存的DML优于最近的基于小批量的方法。但是权衡正数对没有帮助。这导致设计加权方案的有效但出乎意料的简单规则，使其与现有的基于小批量的方法显着不同，现有的基于小批量的方法精心设计了各种复杂的损失函数以加权对。最后，我们在三个大型视觉检索基准上进行了广泛的实验，并通过使用带有动量更新的内存的简单对比损失，证明了基于内存的DML优于最近的基于小批量的方法。但是权衡正数对没有帮助。这导致设计加权方案的有效但出乎意料的简单规则，使其与现有的基于小批量的方法显着不同，现有的基于小批量的方法精心设计了各种复杂的损失函数以加权对。最后，我们在三个大型视觉检索基准上进行了广泛的实验，并通过使用带有动量更新的内存的简单对比损失，证明了基于内存的DML优于最近的基于小批量的方法。