Hyp-uml: Hyperbolic Image Retrieval With Uncertainty-aware Metric Learning

Abstract

Metric learning plays a critical role in training image retrieval and classification. It is also a key algorithm in representation learning, e.g., for feature learning and its alignment in metric space. Hyperbolic embedding has been recently developed. Compared to the conventional Euclidean embedding in most of the previously developed models, Hyperbolic embedding can be more effective in representing the hierarchical data structure. Second, uncertainty estimation/measurement is a long-lasting challenge in artificial intelligence. Successful uncertainty estimation can improve a machine learning model's performance, robustness, and security. In Hyperbolic space, uncertainty measurement is at least with equivalent, if not more, critical importance. In this paper, we develop a Hyperbolic image embedding with uncertainty-aware metric learning for image retrieval. We call our method Hyp-UML: Hyperbolic Uncertainty-aware Metric Learning. Our contribution are threefold: we propose an image em

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyan2023hyp

Related papers

• Hyp\(^2\) Loss: Beyond Hypersphere Metric Space For Multi-label Image Retrieval (2022)13.32
• Introspective Deep Metric Learning For Image Retrieval (2022)3.50
• Bayesian Metric Learning For Uncertainty Quantification In Image Retrieval (2023)0.00
• Introspective Deep Metric Learning (2023)13.85
• Large-scale Distance Metric Learning With Uncertainty (2018)9.03
• Hyperbolic Image Embeddings (2019)17.91
• Piecewise-linear Manifolds For Deep Metric Learning (2024)0.00
• Bayesian Triplet Loss: Uncertainty Quantification In Image Retrieval (2020)11.49