Deep Metric Learning Using Similarities From Nonlinear Rank Approximations

Abstract

In recent years, deep metric learning has achieved promising results in learning high dimensional semantic feature embeddings where the spatial relationships of the feature vectors match the visual similarities of the images. Similarity search for images is performed by determining the vectors with the smallest distances to a query vector. However, high retrieval quality does not depend on the actual distances of the feature vectors, but rather on the ranking order of the feature vectors from similar images. In this paper, we introduce a metric learning algorithm that focuses on identifying and modifying those feature vectors that most strongly affect the retrieval quality. We compute normalized approximated ranks and convert them to similarities by applying a nonlinear transfer function. These similarities are used in a newly proposed loss function that better contracts similar and disperses dissimilar samples. Experiments demonstrate significant improvement over existing deep feature

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyschall2019deep

Related papers

• Sharing Matters For Generalization In Deep Metric Learning (2020)8.35
• Learning Non-metric Visual Similarity For Image Retrieval (2017)11.58
• Deep Metric Learning Assisted By Intra-variance In A Semi-supervised View Of Learning (2023)5.24
• Darkrank: Accelerating Deep Metric Learning Via Cross Sample Similarities Transfer (2017)14.87
• Directional Statistics-based Deep Metric Learning For Image Classification And Retrieval (2018)13.05
• Supervised Metric Learning To Rank For Retrieval Via Contextual Similarity Optimization (2022)2.64
• Deep Metric Learning For Computer Vision: A Brief Overview (2023)6.77
• Metric Learning By Similarity Network For Deep Semi-supervised Learning (2020)3.58