{"ID":5438824,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T11:20:51.789462812Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31517","arxiv_id":"2606.31517","title":"Unsupervised Data-Efficient Cross-Modal Retrieval with Global-Neighborhood Alignment Hashing","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2606.31517","url_pdf":"https://arxiv.org/pdf/2606.31517v1","authors":"[\"Runhao Li\",\"Xiaoxu Ma\",\"Zhenyu Weng\",\"Yue Zhang\",\"Guibo Luo\",\"Huiping Zhuang\",\"Zhiping Lin\",\"Yap-Peng Tan\"]","published":"2026-06-30T11:30:53Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.CV\"]","methods":"[]","has_code":false}