Adversarial Metric Learning

02/09/2018
by   Shuo Chen, et al.
0

In the past decades, intensive efforts have been put to design various loss functions and metric forms for metric learning problem. These improvements have shown promising results when the test data is similar to the training data. However, the trained models often fail to produce reliable distances on the ambiguous test pairs due to the distribution bias between training set and test set. To address this problem, the Adversarial Metric Learning (AML) is proposed in this paper, which automatically generates adversarial pairs to remedy the distribution bias and facilitate robust metric learning. Specifically, AML consists of two adversarial stages, i.e. confusion and distinguishment. In confusion stage, the ambiguous but critical adversarial data pairs are adaptively generated to mislead the learned metric. In distinguishment stage, a metric is exhaustively learned to try its best to distinguish both the adversarial pairs and the original training pairs. Thanks to the challenges posed by the confusion stage in such competing process, the AML model is able to grasp plentiful difficult knowledge that has not been contained by the original training pairs, so the discriminability of AML can be significantly improved. The entire model is formulated into optimization framework, of which the global convergence is theoretically proved. The experimental results on toy data and practical datasets clearly demonstrate the superiority of AML to the representative state-of-the-art metric learning methodologies.

READ FULL TEXT
research
08/18/2020

Positive semidefinite support vector regression metric learning

Most existing metric learning methods focus on learning a similarity or ...
research
04/04/2019

Signal-to-Noise Ratio: A Robust Distance Metric for Deep Metric Learning

Deep metric learning, which learns discriminative features to process im...
research
05/03/2017

Lifelong Metric Learning

The state-of-the-art online learning approaches are only capable of lear...
research
03/28/2021

Hierarchical Relationship Alignment Metric Learning

Most existing metric learning methods focus on learning a similarity or ...
research
09/16/2023

Universal Metric Learning with Parameter-Efficient Transfer Learning

A common practice in metric learning is to train and test an embedding m...
research
06/10/2020

Towards Certified Robustness of Metric Learning

Metric learning aims to learn a distance metric such that semantically s...
research
12/24/2019

a simple and effective framework for pairwise deep metric learning

Deep metric learning (DML) has received much attention in deep learning ...

Please sign up or login with your details

Forgot password? Click here to reset