# Unsupervised Data-Efficient Cross-Modal Retrieval with Global-Neighborhood Alignment Hashing

arXiv: https://arxiv.org/abs/2606.31517 · HTML: https://mlsanity.com/paper/2606.31517/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 27 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Builds on (most cited first, 9 of 9)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [Deep Cross-Modal Hashing](https://mlsanity.com/paper/1602.02255/) (2016)
- [Supervised Discrete Hashing](https://mlsanity.com/paper/1503.01557/) (2015)
- [Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning](https://mlsanity.com/paper/2307.03073/) (2023)

## Built on by (most cited first, 1 of 1)

- [Attribute-Prompted Kernel Hashing for Unsupervised Data-Efficient Cross-Modal Retrieval](https://mlsanity.com/paper/2607.00379/) (2026)

## Abstract (arXiv)

Compared to supervised cross-modal hashing (CMH), unsupervised CMH reduces the reliance on manual labeling by learning binary codes from unlabeled image-text pairs. However, existing unsupervised CMH methods often rely on large-scale image-text pairs, which are costly to collect. To address this limitation, we propose Global-Neighborhood Alignment Hashing (GNAH), a novel approach that preserves the semantic structure of vision-language foundation models within a compact binary Hamming space using only a limited number of image-text pairs. Specifically, GNAH captures global structural information from the continuous latent space and transfers it into the binary Hamming space through a Prototype-Anchored Global Alignment module. In addition, GNAH extends conventional pairwise contrastive learning by modeling stochastic neighborhood relationships via a Contrastive Stochastic Neighborhood Alignment module, thereby alleviating overfitting to sparse pairwise correlations. Extensive experiments demonstrate that GNAH consistently outperforms existing unsupervised cross-modal retrieval methods under data-constrained settings, offering a practical solution for real-world CMH applications.