Multi-head Deep Metric Learning Using Global And Local Representations

Abstract

Deep Metric Learning (DML) models often require strong local and global representations, however, effective integration of local and global features in DML model training is a challenge. DML models are often trained with specific loss functions, including pairwise-based and proxy-based losses. The pairwise-based loss functions leverage rich semantic relations among data points, however, they often suffer from slow convergence during DML model training. On the other hand, the proxy-based loss functions often lead to significant speedups in convergence during training, while the rich relations among data points are often not fully explored by the proxy-based losses. In this paper, we propose a novel DML approach to address these challenges. The proposed DML approach makes use of a hybrid loss by integrating the pairwise-based and the proxy-based loss functions to leverage rich data-to-data relations as well as fast convergence. Furthermore, the proposed DML approach utilizes both global

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keyebrahimpour2021multi

Related papers

• Guided Deep Metric Learning (2022)6.77
• Ensemble Of Loss Functions To Improve Generalizability Of Deep Metric Learning Methods (2021)7.16
• Towards Improved Proxy-based Deep Metric Learning Via Data-augmented Domain Adaptation (2024)6.34
• Improving Deep Metric Learning By Divide And Conquer (2021)8.09
• Ranked List Loss For Deep Metric Learning (2019)7.50
• Revisiting Training Strategies And Generalization Performance In Deep Metric Learning (2020)5.08
• Unbiased Evaluation Of Deep Metric Learning Algorithms (2019)0.00
• Deep Metric Learning With Soft Orthogonal Proxies (2023)0.00