Hierarchical Proxy-based Loss For Deep Metric Learning

Abstract

Proxy-based metric learning losses are superior to pair-based losses due to their fast convergence and low training complexity. However, existing proxy-based losses focus on learning class-discriminative features while overlooking the commonalities shared across classes which are potentially useful in describing and matching samples. Moreover, they ignore the implicit hierarchy of categories in real-world datasets, where similar subordinate classes can be grouped together. In this paper, we present a framework that leverages this implicit hierarchy by imposing a hierarchical structure on the proxies and can be used with any existing proxy-based loss. This allows our model to capture both class-discriminative features and class-shared characteristics without breaking the implicit data hierarchy. We evaluate our method on five established image retrieval datasets such as In-Shop and SOP. Results demonstrate that our hierarchical proxy-based loss framework improves the performance of exis

Stats

• citations27
• S2 citations—
• github stars0
• HF likes0
• heat score10.85
• arxiv keyyang2021hierarchical

Related papers

• Robust Calibrate Proxy Loss For Deep Metric Learning (2023)0.00
• Deep Metric Learning With Soft Orthogonal Proxies (2023)0.00
• Proxy Synthesis: Learning With Synthetic Classes For Deep Metric Learning (2021)10.85
• Informative Sample-aware Proxy For Deep Metric Learning (2022)0.00
• Hyp\(^2\) Loss: Beyond Hypersphere Metric Space For Multi-label Image Retrieval (2022)13.32
• Adaptive Additive Classification-based Loss For Deep Metric Learning (2020)0.00
• Towards Improved Proxy-based Deep Metric Learning Via Data-augmented Domain Adaptation (2024)6.34
• The Group Loss For Deep Metric Learning (2019)11.39