Maintaining Difficulty: A Margin Scheduler for Triplet Loss in Siamese Networks Training

Read full text Summarise with VIRAT
Authors: Roberto Sprengel Minozzo Tomchak, Oge Marques, Lucas Garcia Pedroso, Luiz Eduardo Oliveira, Paulo Ricardo Lisboa de Almeida
Cited by: 0
References: 17

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The Triplet Margin Ranking Loss is one of the most widely used loss functions in Siamese Networks for solving Distance Metric Learning (DML) problems. This loss function depends on a margin parameter μ, which defines the minimum distance that should separate positive and negative pairs during training. In this work, we show that, during training, the effective margin of many triplets often exceeds the predefined value of μ, provided that a sufficient number of triplets violating this margin is observed. This behavior indicates that fixing the margin throughout training may limit the learning process. Based on this observation, we propose a margin scheduler that adjusts the value of μ according to the proportion of easy triplets observed at each epoch, with the goal of maintaining training difficulty over time. We show that the proposed strategy leads to improved performance when compared to both a constant margin and a monotonically increasing margin scheme. Experimental results on four different datasets show consistent gains in verification performance.

Fields of Study & Subjects

Face recognition and analysis Face and Expression Recognition Biometric Identification and Security

Publication details

Journal / source
International Joint Conference on Neural Networks (IJCNN)
Pages
1–6
Publication date
1 June 2026
Language
EN