Balance Act: Mitigating Hubness In Cross-modal Retrieval With Query And Gallery Banks

Abstract

In this work, we present a post-processing solution to address the hubness problem in cross-modal retrieval, a phenomenon where a small number of gallery data points are frequently retrieved, resulting in a decline in retrieval performance. We first theoretically demonstrate the necessity of incorporating both the gallery and query data for addressing hubness as hubs always exhibit high similarity with gallery and query data. Second, building on our theoretical results, we propose a novel framework, Dual Bank Normalization (DBNorm). While previous work has attempted to alleviate hubness by only utilizing the query samples, DBNorm leverages two banks constructed from the query and gallery samples to reduce the occurrence of hubs during inference. Next, to complement DBNorm, we introduce two novel methods, dual inverted softmax and dual dynamic inverted softmax, for normalizing similarity based on the two banks. Specifically, our proposed methods reduce the similarity between hubs and qu

Stats

• citations7
• S2 citations—
• github stars6
• HF likes0
• heat score8.46
• arxiv keywang2023balance

Related papers

• Hubness Reduction With Dual Bank Sinkhorn Normalization For Cross-modal Retrieval (2025)0.95
• Cross Modal Retrieval With Querybank Normalisation (2021)14.06
• Neighborretr: Balancing Hub Centrality In Cross-modal Retrieval (2025)4.17
• Adversarial Hubness In Multi-modal Retrieval (2024)0.00
• 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
• Preserving Semantic Neighborhoods For Robust Cross-modal Retrieval (2020)10.07
• Comprehensive Graph-conditional Similarity Preserving Network For Unsupervised Cross-modal Hashing (2020)3.14