Hubness Reduction With Dual Bank Sinkhorn Normalization For Cross-modal Retrieval
2025 · Zhengxin Pan, Haishuai Wang, Fangyu Wu, et al.
Abstract
The past decade has witnessed rapid advancements in cross-modal retrieval, with significant progress made in accurately measuring the similarity between cross-modal pairs. However, the persistent hubness problem, a phenomenon where a small number of targets frequently appear as nearest neighbors to numerous queries, continues to hinder the precision of similarity measurements. Despite several proposed methods to reduce hubness, their underlying mechanisms remain poorly understood. To bridge this gap, we analyze the widely-adopted Inverted Softmax approach and demonstrate its effectiveness in balancing target probabilities during retrieval. Building on these insights, we propose a probability-balancing framework for more effective hubness reduction. We contend that balancing target probabilities alone is inadequate and, therefore, extend the framework to balance both query and target probabilities by introducing Sinkhorn Normalization (SN). Notably, we extend SN to scenarios where the t
Authors
(none)
Tags
Stats
Related papers
- Balance Act: Mitigating Hubness In Cross-modal Retrieval With Query And Gallery Banks (2023)8.46
- Neighborretr: Balancing Hub Centrality In Cross-modal Retrieval (2025)4.17
- Adversarial Hubness In Multi-modal Retrieval (2024)0.00
- Cross Modal Retrieval With Querybank Normalisation (2021)14.06
- Semantic-consistent Bidirectional Contrastive Hashing For Noisy Multi-label Cross-modal Retrieval (2025)0.00
- Comprehensive Graph-conditional Similarity Preserving Network For Unsupervised Cross-modal Hashing (2020)3.14
- HAL: Improved Text-image Matching By Mitigating Visual Semantic Hubs (2019)10.48
- Maximal Matching Matters: Preventing Representation Collapse For Robust Cross-modal Retrieval (2025)2.26