使用基于内存的虚拟类进行深度度量学习
Learning with Memory-based Virtual Classes for Deep Metric Learning
摘要：
深度度量学习（DML）的核心是在高维嵌入空间中学习视觉相似性。主要挑战之一是从可见的训练数据类推广到不可见的测试数据类。最近的工作集中在利用过去的嵌入，以增加所看到的类的实例的数量。这些方法通过增强来实现性能改进，而对可见类的强烈关注仍然存在。这对于DML来说是不可取的，因为训练数据和测试数据表现出完全不同的类。在这项工作中，我们提出了一种新的DML训练策略，称为MemVir。与以前的作品不同，MemVir记住了嵌入特征和类权重，以将它们用作额外的虚拟类。虚拟类的开发不仅利用了增强的信息进行训练，而且还强调了对可见类的关注，以获得更好的泛化能力。此外，我们还嵌入了课程学习的思想，通过缓慢添加虚拟班级来逐步增加学习难度，从而提高学习稳定性以及最终表现。MemVir可以很容易地应用于许多现有的损失函数，而不需要任何修改。在著名的基准测试上进行的大量实验结果证明了MemVir优于最先进的竞争对手。MemVir的代码是公开的。
英文摘要：
The core of deep metric learning (DML) involves learning visual similarities in high-dimensional embedding space. One of the main challenges is to generalize from seen classes of training data to unseen classes of test data. Recent works have focused on exploiting past embeddings to increase the number of instances for the seen classes. Such methods achieve performance improvement via augmentation, while the strong focus on seen classes still remains. This can be undesirable for DML, where training and test data exhibit entirely different classes. In this work, we present a novel training strategy for DML called MemVir. Unlike previous works, MemVir memorizes both embedding features and class weights to utilize them as additional virtual classes. The exploitation of virtual classes not only utilizes augmented information for training but also alleviates a strong focus on seen classes for better generalization. Moreover, we embed the idea of curriculum learning by slowly adding virtual classes for a gradual increase in learning difficulty, which improves the learning stability as well as the final performance. MemVir can be easily applied to many existing loss functions without any modification. Extensive experimental results on famous benchmarks demonstrate the superiority of MemVir over state-of-the-art competitors. Code of MemVir is publicly available.
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。
