Learning to Generate Novel Classes for Deep Metric Learning

01/04/2022
by   Kyungmoon Lee, et al.
0

Deep metric learning aims to learn an embedding space where the distance between data reflects their class equivalence, even when their classes are unseen during training. However, the limited number of classes available in training precludes generalization of the learned embedding space. Motivated by this, we introduce a new data augmentation approach that synthesizes novel classes and their embedding vectors. Our approach can provide rich semantic information to an embedding model and improve its generalization by augmenting training data with novel classes unavailable in the original data. We implement this idea by learning and exploiting a conditional generative model, which, given a class label and a noise, produces a random embedding vector of the class. Our proposed generator allows the loss to use richer class relations by augmenting realistic and diverse classes, resulting in better generalization to unseen samples. Experimental results on public benchmark datasets demonstrate that our method clearly enhances the performance of proxy-based losses.

READ FULL TEXT

page 2

page 6

page 8

research
03/29/2021

Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning

One of the main purposes of deep metric learning is to construct an embe...
research
03/18/2020

OpenGAN: Open Set Generative Adversarial Networks

Many existing conditional Generative Adversarial Networks (cGANs) are li...
research
10/09/2022

Coded Residual Transform for Generalizable Deep Metric Learning

A fundamental challenge in deep metric learning is the generalization ca...
research
02/19/2020

Revisiting Training Strategies and Generalization Performance in Deep Metric Learning

Deep Metric Learning (DML) is arguably one of the most influential lines...
research
03/01/2023

Domain-aware Triplet loss in Domain Generalization

Despite much progress being made in the field of object recognition with...
research
03/31/2021

Learning with Memory-based Virtual Classes for Deep Metric Learning

The core of deep metric learning (DML) involves learning visual similari...
research
03/27/2021

Embedding Transfer with Label Relaxation for Improved Metric Learning

This paper presents a novel method for embedding transfer, a task of tra...

Please sign up or login with your details

Forgot password? Click here to reset