Guided Deep Metric Learning

Abstract

Deep Metric Learning (DML) methods have been proven relevant for visual similarity learning. However, they sometimes lack generalization properties because they are trained often using an inappropriate sample selection strategy or due to the difficulty of the dataset caused by a distributional shift in the data. These represent a significant drawback when attempting to learn the underlying data manifold. Therefore, there is a pressing need to develop better ways of obtaining generalization and representation of the underlying manifold. In this paper, we propose a novel approach to DML that we call Guided Deep Metric Learning, a novel architecture oriented to learning more compact clusters, improving generalization under distributional shifts in DML. This novel architecture consists of two independent models: A multi-branch master model, inspired from a Few-Shot Learning (FSL) perspective, generates a reduced hypothesis space based on prior knowledge from labeled data, which guides or r

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keygonzalezzapata2022guided

Related papers

• Improving Deep Metric Learning By Divide And Conquer (2021)8.09
• Integrating Language Guidance Into Vision-based Deep Metric Learning (2022)14.04
• Revisiting Training Strategies And Generalization Performance In Deep Metric Learning (2020)5.08
• A Framework To Enhance Generalization Of Deep Metric Learning Methods Using General Discriminative Feature Learning And Class Adversarial Neural Networks (2021)7.50
• Diva: Diverse Visual Feature Aggregation For Deep Metric Learning (2020)11.58
• Multi-head Deep Metric Learning Using Global And Local Representations (2021)6.77
• S2SD: Simultaneous Similarity-based Self-distillation For Deep Metric Learning (2020)3.31
• Indirect: Language-guided Zero-shot Deep Metric Learning For Images (2022)5.24