Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning

03/29/2021
by   Geonmo Gu, et al.
56

One of the main purposes of deep metric learning is to construct an embedding space that has well-generalized embeddings on both seen (training) classes and unseen (test) classes. Most existing works have tried to achieve this using different types of metric objectives and hard sample mining strategies with given training data. However, learning with only the training data can be overfitted to the seen classes, leading to the lack of generalization capability on unseen classes. To address this problem, we propose a simple regularizer called Proxy Synthesis that exploits synthetic classes for stronger generalization in deep metric learning. The proposed method generates synthetic embeddings and proxies that work as synthetic classes, and they mimic unseen classes when computing proxy-based losses. Proxy Synthesis derives an embedding space considering class relations and smooth decision boundaries for robustness on unseen classes. Our method is applicable to any proxy-based losses, including softmax and its variants. Extensive experiments on four famous benchmarks in image retrieval tasks demonstrate that Proxy Synthesis significantly boosts the performance of proxy-based losses and achieves state-of-the-art performance.

READ FULL TEXT

page 4

page 6

page 17

page 22

research
01/04/2022

Learning to Generate Novel Classes for Deep Metric Learning

Deep metric learning aims to learn an embedding space where the distance...
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
03/31/2020

Proxy Anchor Loss for Deep Metric Learning

Existing metric learning losses can be categorized into two classes: pai...
research
06/22/2023

Deep Metric Learning with Soft Orthogonal Proxies

Deep Metric Learning (DML) models rely on strong representations and sim...
research
11/18/2022

Informative Sample-Aware Proxy for Deep Metric Learning

Among various supervised deep metric learning methods proxy-based approa...
research
07/08/2022

A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning

Proxy-based Deep Metric Learning (DML) learns deep representations by em...
research
03/25/2021

Hierarchical Proxy-based Loss for Deep Metric Learning

Proxy-based metric learning losses are superior to pair-based losses due...

Please sign up or login with your details

Forgot password? Click here to reset