Construct Informative Triplet with Two-stage Hard-sample Generation

12/04/2021
by   Chuang Zhu, et al.
0

In this paper, we propose a robust sample generation scheme to construct informative triplets. The proposed hard sample generation is a two-stage synthesis framework that produces hard samples through effective positive and negative sample generators in two stages, respectively. The first stage stretches the anchor-positive pairs with piecewise linear manipulation and enhances the quality of generated samples by skillfully designing a conditional generative adversarial network to lower the risk of mode collapse. The second stage utilizes an adaptive reverse metric constraint to generate the final hard samples. Extensive experiments on several benchmark datasets verify that our method achieves superior performance than the existing hard-sample generation algorithms. Besides, we also find that our proposed hard sample generation method combining the existing triplet mining strategies can further boost the deep metric learning performance.

READ FULL TEXT

page 25

page 29

research
01/31/2020

Symmetrical Synthesis for Deep Metric Learning

Deep metric learning aims to learn embeddings that contain semantic simi...
research
10/18/2022

No Pairs Left Behind: Improving Metric Learning with Regularized Triplet Objective

We propose a novel formulation of the triplet objective function that im...
research
12/17/2018

Learning Incremental Triplet Margin for Person Re-identification

Person re-identification (ReID) aims to match people across multiple non...
research
06/17/2022

Improving Generalization of Metric Learning via Listwise Self-distillation

Most deep metric learning (DML) methods employ a strategy that forces al...
research
03/13/2019

Hardness-Aware Deep Metric Learning

This paper presents a hardness-aware deep metric learning (HDML) framewo...
research
11/09/2020

Robust Visual Tracking via Statistical Positive Sample Generation and Gradient Aware Learning

In recent years, Convolutional Neural Network (CNN) based trackers have ...
research
06/11/2020

Improving Deep Metric Learning with Virtual Classes and Examples Mining

In deep metric learning, the training procedure relies on sampling infor...

Please sign up or login with your details

Forgot password? Click here to reset