In this work, we propose the margin preserving metric learning framework to learn the distance metric and latent examples simultaneously. By leveraging the ...

May 25, 2018 · In this work, we propose the margin preserving metric learning framework to learn the distance metric and latent examples simultaneously. By ...

Distance metric learning (DML) has been studied ex- tensively in the past decades for its superior performance with distance-based algorithms.

In this work, we propose the margin preserving metric learning framework to learn the distance metric and latent examples simultaneously. By leveraging the ...

This work proposes the margin preserving metric learning framework to learn the distance metric and latent examples simultaneously and shows that the metric ...

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 ...

Bibliographic details on Large-scale Distance Metric Learning with Uncertainty.

Additionally, this sampling typically makes metric learning computationally intractable on large-scale datasets, such as CIFAR10, CIFAR100 or ImageNet [25] .

Signal-to-Noise Ratio: A Robust Distance Metric for Deep Metric Learning (CVPR) [paper] ... Large-Scale Distance Metric Learning with Uncertainty (CVPR) [paper].

Distance metric learning is a category of machine learning algorithms that extracts similarity information from the input features themselves.