论文标题
嵌入扩展：嵌入深度度量学习空间的增强
Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning
论文作者
论文摘要
研究了样品对之间的距离度量，以进行图像检索和聚类。随着基于成对的度量学习损失的显着成功，最近的作品提出了在公制学习损失增加和泛化的制定合成点上的使用。但是，这些方法需要其他生成网络以及主网络，这可能会导致较大的模型大小，较慢的训练速度和更难的优化。同时，后处理技术（例如查询扩展和数据库增强）提出了功能点的组合，以获取其他语义信息。在本文中，受查询扩展和数据库增强的启发，我们在嵌入基于成对的度量学习损失的嵌入空间中提出了一种增强方法，称为嵌入式扩展。所提出的方法通过特征点的组合生成包含增强信息的合成点，并执行硬性对挖掘以学习最有用的特征表示。由于其简单性和灵活性，它可用于现有的度量学习损失，而不会影响模型大小，训练速度或优化难度。最后，在图像检索任务和聚类任务中，嵌入扩展和代表性度量学习损失的组合优于最新损失和先前的样本生成方法。该实施已公开可用。
Learning the distance metric between pairs of samples has been studied for image retrieval and clustering. With the remarkable success of pair-based metric learning losses, recent works have proposed the use of generated synthetic points on metric learning losses for augmentation and generalization. However, these methods require additional generative networks along with the main network, which can lead to a larger model size, slower training speed, and harder optimization. Meanwhile, post-processing techniques, such as query expansion and database augmentation, have proposed the combination of feature points to obtain additional semantic information. In this paper, inspired by query expansion and database augmentation, we propose an augmentation method in an embedding space for pair-based metric learning losses, called embedding expansion. The proposed method generates synthetic points containing augmented information by a combination of feature points and performs hard negative pair mining to learn with the most informative feature representations. Because of its simplicity and flexibility, it can be used for existing metric learning losses without affecting model size, training speed, or optimization difficulty. Finally, the combination of embedding expansion and representative metric learning losses outperforms the state-of-the-art losses and previous sample generation methods in both image retrieval and clustering tasks. The implementation is publicly available.
