Ensemble Of Loss Functions To Improve Generalizability Of Deep Metric Learning Methods

Abstract

Deep Metric Learning (DML) learns a non-linear semantic embedding from input data that brings similar pairs together while keeping dissimilar data away from each other. To this end, many different methods are proposed in the last decade with promising results in various applications. The success of a DML algorithm greatly depends on its loss function. However, no loss function is perfect, and it deals only with some aspects of an optimal similarity embedding. Besides, the generalizability of the DML on unseen categories during the test stage is an important matter that is not considered by existing loss functions. To address these challenges, we propose novel approaches to combine different losses built on top of a shared deep feature extractor. The proposed ensemble of losses enforces the deep model to extract features that are consistent with all losses. Since the selected losses are diverse and each emphasizes different aspects of an optimal semantic embedding, our effective combini

Stats

• citations8
• S2 citations—
• github stars0
• HF likes0
• heat score7.16
• arxiv keyzabihzadeh2021ensemble

Related papers

• Ranked List Loss For Deep Metric Learning (2019)7.50
• Multi-head Deep Metric Learning Using Global And Local Representations (2021)6.77
• A Framework To Enhance Generalization Of Deep Metric Learning Methods Using General Discriminative Feature Learning And Class Adversarial Neural Networks (2021)7.50
• The Group Loss For Deep Metric Learning (2019)11.39
• Anti-collapse Loss For Deep Metric Learning Based On Coding Rate Metric (2024)0.00
• Revisiting Training Strategies And Generalization Performance In Deep Metric Learning (2020)5.08
• Guided Deep Metric Learning (2022)6.77
• The Group Loss++: A Deeper Look Into Group Loss For Deep Metric Learning (2022)8.82