# Balance Act: Mitigating Hubness in Cross-Modal Retrieval with Query and Gallery Banks

arXiv: https://arxiv.org/abs/2310.11612 · HTML: https://mlsanity.com/paper/2310.11612/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 98 references that are in the map.
- First posted on arXiv 17 Oct 2023.

## Builds on (most cited first, 30 of 57)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling](https://mlsanity.com/paper/2102.06183/) (2021)
- [Multi-modal Transformer for Video Retrieval](https://mlsanity.com/paper/2007.10639/) (2020)
- [HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training](https://mlsanity.com/paper/2005.00200/) (2020)
- [Clotho: An Audio Captioning Dataset](https://mlsanity.com/paper/1910.09387/) (2019)
- [Large-Scale Adversarial Training for Vision-and-Language Representation Learning](https://mlsanity.com/paper/2006.06195/) (2020)
- [X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval](https://mlsanity.com/paper/2207.07285/) (2022)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Use What You Have: Video Retrieval Using Representations From Collaborative Experts](https://mlsanity.com/paper/1907.13487/) (2019)
- [Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning](https://mlsanity.com/paper/2003.00392/) (2020)
- [Support-set bottlenecks for video-text representation learning](https://mlsanity.com/paper/2010.02824/) (2020)
- [X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval](https://mlsanity.com/paper/2203.15086/) (2022)
- [Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss](https://mlsanity.com/paper/2109.04290/) (2021)
- [TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval](https://mlsanity.com/paper/2207.07852/) (2022)

## Built on by (most cited first, 20 of 20)

- [Domain Prompt Learning with Quaternion Networks](https://mlsanity.com/paper/2312.08878/) (2023)
- [To Align or Not to Align: Strategic Multimodal Representation Alignment for Optimal Performance](https://mlsanity.com/paper/2511.12121/) (2025)
- [Nearest Neighbor Normalization Improves Multimodal Retrieval](https://mlsanity.com/paper/2410.24114/) (2024)
- [NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval](https://mlsanity.com/paper/2503.10526/) (2025)
- [Cache Mechanism for Agent RAG Systems](https://mlsanity.com/paper/2511.02919/) (2025)
- [Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language](https://mlsanity.com/paper/2605.29793/) (2026)
- [InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution](https://mlsanity.com/paper/2310.13276/) (2023)
- [LEO-MINI: An Efficient Multimodal Large Language Model using Conditional Token Reduction and Mixture of Multi-Modal Experts](https://mlsanity.com/paper/2504.04653/) (2025)
- [DREAM: Improving Video-Text Retrieval Through Relevance-Based Augmentation Using Large Foundation Models](https://mlsanity.com/paper/2404.05083/) (2024)
- [Prediction hubs are context-informed frequent tokens in LLMs](https://mlsanity.com/paper/2502.10201/) (2025)
- [Adversarial Hubness Detector: Detecting Hubness Poisoning in Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2602.22427/) (2026)
- [One Single Hub Text Breaks CLIP: Identifying Vulnerabilities in Cross-Modal Encoders via Hubness](https://mlsanity.com/paper/2604.27674/) (2026)
- [Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval](https://mlsanity.com/paper/2505.12499/) (2025)
- [LLM-enhanced Action-aware Multi-modal Prompt Tuning for Image-Text Matching](https://mlsanity.com/paper/2506.23502/) (2025)
- [Hacking Neural Evaluation Metrics with Single Hub Text](https://mlsanity.com/paper/2512.16323/) (2025)
- [Query-aware Hub Prototype Learning for Few-Shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2512.08253/) (2025)
- [Robust Test-time Video-Text Retrieval: Benchmarking and Adapting for Query Shifts](https://mlsanity.com/paper/2604.20851/) (2026)
- [Turing Patterns for Multimedia: Reaction-Diffusion Multi-Modal Fusion for Language-Guided Video Moment Retrieval](https://mlsanity.com/paper/2606.01615/) (2026)
- [When Modality Gap Reduction Fails: Prediction-Level Hubness in CLIP](https://mlsanity.com/paper/2609.01103/) (2026)
- [MINER: Multi-crop INference-time Enhancement for Rare-Object Retrieval with Frozen Dual Encoders](https://mlsanity.com/paper/2609.27142/) (2026)

## Abstract (arXiv)

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 queries while improving the similarity between non-hubs and queries. Finally, we present extensive experimental results on diverse language-grounded benchmarks, including text-image, text-video, and text-audio, demonstrating the superior performance of our approaches compared to previous methods in addressing hubness and boosting retrieval performance. Our code is available at https://github.com/yimuwangcs/Better_Cross_Modal_Retrieval.