Deep metric learning for visual understanding : an overview of recent advances

• Main Authors: Lu, Jiwen, Hu, Junlin, Zhou, Jie
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2020
• Subjects: Engineering::Electrical and electronic engineering; Neural Networks; Visualization
• Online Access: https://hdl.handle.net/10356/142292
• Institution: Nanyang Technological University

Metric learning aims to learn a distance function to measure the similarity of samples, which plays an important role in many visual understanding applications. Generally, the optimal similarity functions for different visual understanding tasks are task specific because the distributions for data u...