Deep Metric Learning: A Survey

By Mahmut Kaya, H. Ş. Bilge. Symmetry, 2019

733 citations recorded by the source corpus.

Metric learning aims to measure the similarity among samples while using an optimal distance metric for learning tasks. Metric learning methods, which generally use a linear projection, are limited in solving real-world problems demonstrating non-linear characteristics. Kernel approaches are utilized in metric learning to address this problem. In recent years, deep metric learning, which provides a better solution for nonlinear data through activation functions, has attracted researchers' attention in many different areas. This article aims to reveal the importance of deep metric learning and the problems dealt with in this field in the light of recent studies. As far as the research conducted in this field are concerned, most existing studies that are inspired by Siamese and Triplet networks are commonly used to correlate among samples while using shared weights in deep metric learning. The success of these networks is based on their capacity to understand the similarity relationship among samples. Moreover, sampling strategy, appropriate distance metric, and the structure of the network are the challenging factors for researchers to improve the performance of the network model. This article is considered to be important, as it is the first comprehensive study in which these factors are systematically analyzed and evaluated as a whole and supported by comparing the quantitative results of the methods.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a71503ac83cd62519c3e4004dc25c8f98764b184

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Exploring Cross-Image Pixel Contrast for Semantic Segmentation (2021, background): “Previous works have confirmed that hard negatives are crucial for metric learning [39, 60, 62], and our study further reveals the importance of mining both informative negatives/positives and anchors in this supervised, dense image prediction task.”
Dataset Meta-Learning from Kernel Ridge-Regression (2020, methodology): “Kernel methods or instance-based learning (Vinyals et al., 2016; Snell et al., 2017; Kaya & Bilge, 2019) in general require a support dataset to be deployed at inference time.”
Improving transfer of expressivity for end-to-end multispeaker text-to-speech synthesis (2021, methodology): “In this paper, we present a novel metric learning framework [13] jointly trained with a Tacotron 2 based end-to-end TTS system [14].”