Large-scale Distance Metric Learning With Uncertainty

Abstract

Distance metric learning (DML) has been studied extensively in the past decades for its superior performance with distance-based algorithms. Most of the existing methods propose to learn a distance metric with pairwise or triplet constraints. However, the number of constraints is quadratic or even cubic in the number of the original examples, which makes it challenging for DML to handle the large-scale data set. Besides, the real-world data may contain various uncertainty, especially for the image data. The uncertainty can mislead the learning procedure and cause the performance degradation. By investigating the image data, we find that the original data can be observed from a small set of clean latent examples with different distortions. In this work, we propose the margin preserving metric learning framework to learn the distance metric and latent examples simultaneously. By leveraging the ideal properties of latent examples, the training efficiency can be improved significantly whil

Stats

• citations15
• S2 citations—
• github stars0
• HF likes0
• heat score9.03
• arxiv keyqian2018large

Related papers

• No Fuss Distance Metric Learning Using Proxies (2017)20.03
• Guided Deep Metric Learning (2022)6.77
• Piecewise-linear Manifolds For Deep Metric Learning (2024)0.00
• Improving Deep Metric Learning By Divide And Conquer (2021)8.09
• Unbiased Evaluation Of Deep Metric Learning Algorithms (2019)0.00
• A Framework To Enhance Generalization Of Deep Metric Learning Methods Using General Discriminative Feature Learning And Class Adversarial Neural Networks (2021)7.50
• Hyp-uml: Hyperbolic Image Retrieval With Uncertainty-aware Metric Learning (2023)0.00
• Directional Statistics-based Deep Metric Learning For Image Classification And Retrieval (2018)13.05