Ranked List Loss For Deep Metric Learning

Abstract

The objective of deep metric learning (DML) is to learn embeddings that can capture semantic similarity and dissimilarity information among data points. Existing pairwise or tripletwise loss functions used in DML are known to suffer from slow convergence due to a large proportion of trivial pairs or triplets as the model improves. To improve this, ranking-motivated structured losses are proposed recently to incorporate multiple examples and exploit the structured information among them. They converge faster and achieve state-of-the-art performance. In this work, we unveil two limitations of existing ranking-motivated structured losses and propose a novel ranked list loss to solve both of them. First, given a query, only a fraction of data points is incorporated to build the similarity structure. Consequently, some useful examples are ignored and the structure is less informative. To address this, we propose to build a set-based similarity structure by exploiting all instances in the ga

Stats

• citations9
• S2 citations—
• github stars0
• HF likes0
• heat score7.50
• arxiv keywang2019ranked

Related papers

• Ensemble Of Loss Functions To Improve Generalizability Of Deep Metric Learning Methods (2021)7.16
• Unbiased Evaluation Of Deep Metric Learning Algorithms (2019)0.00
• Anti-collapse Loss For Deep Metric Learning Based On Coding Rate Metric (2024)0.00
• Multi-head Deep Metric Learning Using Global And Local Representations (2021)6.77
• The Group Loss For Deep Metric Learning (2019)11.39
• Constellation Loss: Improving The Efficiency Of Deep Metric Learning Loss Functions For Optimal Embedding (2019)0.00
• Guided Deep Metric Learning (2022)6.77
• Revisiting Training Strategies And Generalization Performance In Deep Metric Learning (2020)5.08