Hyp\(^2\) Loss: Beyond Hypersphere Metric Space For Multi-label Image Retrieval

Abstract

Image retrieval has become an increasingly appealing technique with broad multimedia application prospects, where deep hashing serves as the dominant branch towards low storage and efficient retrieval. In this paper, we carried out in-depth investigations on metric learning in deep hashing for establishing a powerful metric space in multi-label scenarios, where the pair loss suffers high computational overhead and converge difficulty, while the proxy loss is theoretically incapable of expressing the profound label dependencies and exhibits conflicts in the constructed hypersphere space. To address the problems, we propose a novel metric learning framework with Hybrid Proxy-Pair Loss (HyP\(^2\) Loss) that constructs an expressive metric space with efficient training complexity w.r.t. the whole dataset. The proposed HyP\(^2\) Loss focuses on optimizing the hypersphere space by learnable proxies and excavating data-to-data correlations of irrelevant pairs, which integrates sufficient data

Stats

• citations28
• S2 citations—
• github stars14
• HF likes0
• heat score13.32
• arxiv keyxu2022hyp

Related papers

• Improved Deep Hashing With Soft Pairwise Similarity For Multi-label Image Retrieval (2018)16.82
• Hierarchical Proxy-based Loss For Deep Metric Learning (2021)10.85
• Hyp-uml: Hyperbolic Image Retrieval With Uncertainty-aware Metric Learning (2023)0.00
• Hierarchy Neighborhood Discriminative Hashing For An Unified View Of Single-label And Multi-label Image Retrieval (2019)0.00
• Adaptive Asymmetric Label-guided Hashing For Multimedia Search (2022)0.00
• Deep Class-guided Hashing For Multi-label Cross-modal Retrieval (2024)6.20
• Transductive Zero-shot Hashing For Multilabel Image Retrieval (2019)8.82
• Instance-weighted Central Similarity For Multi-label Image Retrieval (2021)0.00