Deep Metric Learning Via Facility Location

Abstract

Learning the representation and the similarity metric in an end-to-end fashion with deep networks have demonstrated outstanding results for clustering and retrieval. However, these recent approaches still suffer from the performance degradation stemming from the local metric training procedure which is unaware of the global structure of the embedding space. We propose a global metric learning scheme for optimizing the deep metric embedding with the learnable clustering function and the clustering metric (NMI) in a novel structured prediction framework. Our experiments on CUB200-2011, Cars196, and Stanford online products datasets show state of the art performance both on the clustering and retrieval tasks measured in the NMI and Recall@K evaluation metrics.

Stats

• citations193
• S2 citations—
• github stars0
• HF likes0
• heat score17.16
• arxiv keysong2016deep

Related papers

• Deep Metric Learning Meets Deep Clustering: An Novel Unsupervised Approach For Feature Embedding (2020)2.26
• Deep Metric Structured Learning For Facial Expression Recognition (2020)0.00
• Deep Relational Metric Learning (2021)12.17
• Deep Metric Learning For Computer Vision: A Brief Overview (2023)6.77
• Guided Deep Metric Learning (2022)6.77
• The Group Loss For Deep Metric Learning (2019)11.39
• Directional Statistics-based Deep Metric Learning For Image Classification And Retrieval (2018)13.05
• Local Similarity-aware Deep Feature Embedding (2016)0.00