Deep Randomized Ensembles For Metric Learning

Abstract

Learning embedding functions, which map semantically related inputs to nearby locations in a feature space supports a variety of classification and information retrieval tasks. In this work, we propose a novel, generalizable and fast method to define a family of embedding functions that can be used as an ensemble to give improved results. Each embedding function is learned by randomly bagging the training labels into small subsets. We show experimentally that these embedding ensembles create effective embedding functions. The ensemble output defines a metric space that improves state of the art performance for image retrieval on CUB-200-2011, Cars-196, In-Shop Clothes Retrieval and VehicleID.

Stats

• citations72
• S2 citations—
• github stars0
• HF likes0
• heat score13.97
• arxiv keyxuan2018deep

Related papers

• Attention-based Ensemble For Deep Metric Learning (2018)15.90
• Deep Metric Learning With BIER: Boosting Independent Embeddings Robustly (2018)14.55
• Generalization In Metric Learning: Should The Embedding Layer Be The Embedding Layer? (2018)8.60
• Deep Metric Learning Assisted By Intra-variance In A Semi-supervised View Of Learning (2023)5.24
• Divide And Conquer The Embedding Space For Metric Learning (2019)14.39
• Semi-supervised Deep Learning By Metric Embedding (2016)0.00
• Deep Relational Metric Learning (2021)12.17
• Visualizing How Embeddings Generalize (2019)0.00