Revisiting Training Strategies And Generalization Performance In Deep Metric Learning

Abstract

Deep Metric Learning (DML) is arguably one of the most influential lines of research for learning visual similarities with many proposed approaches every year. Although the field benefits from the rapid progress, the divergence in training protocols, architectures, and parameter choices make an unbiased comparison difficult. To provide a consistent reference point, we revisit the most widely used DML objective functions and conduct a study of the crucial parameter choices as well as the commonly neglected mini-batch sampling process. Under consistent comparison, DML objectives show much higher saturation than indicated by literature. Further based on our analysis, we uncover a correlation between the embedding space density and compression to the generalization performance of DML models. Exploiting these insights, we propose a simple, yet effective, training regularization to reliably boost the performance of ranking-based DML models on various standard benchmark datasets. Code and a p

Stats

• citations0
• S2 citations—
• github stars344
• HF likes0
• heat score5.08
• arxiv keyroth2020revisiting

Related papers

• Guided Deep Metric Learning (2022)6.77
• Improving Deep Metric Learning By Divide And Conquer (2021)8.09
• Unbiased Evaluation Of Deep Metric Learning Algorithms (2019)0.00
• S2SD: Simultaneous Similarity-based Self-distillation For Deep Metric Learning (2020)3.31
• Integrating Language Guidance Into Vision-based Deep Metric Learning (2022)14.04
• Learning With Memory-based Virtual Classes For Deep Metric Learning (2021)9.92
• A Framework To Enhance Generalization Of Deep Metric Learning Methods Using General Discriminative Feature Learning And Class Adversarial Neural Networks (2021)7.50
• Ensemble Of Loss Functions To Improve Generalizability Of Deep Metric Learning Methods (2021)7.16