Metraipolis › archive › dc_d1c28ddf561e

RegRet: Enhancing Region-Level Retrieval in Large Multimodal Models — arXiv:2609.16847

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16847
License (as archived)
CC0-1.0
Archived
2026-10-15T18:38:40.908Z
SHA-256 of the archived text
21fc2fabb72edff0d8990293cb4ea4ece677088de10731f9c71f74dde4d140ac
Stable URL of this page
https://metraipolis.com/documento/dc_d1c28ddf561e

How to cite

RegRet: Enhancing Region-Level Retrieval in Large Multimodal Models — arXiv:2609.16847 — arXiv (en), https://arxiv.org/abs/2609.16847 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d1c28ddf561e (Metraipolis archive dc_d1c28ddf561e, sha256 21fc2fabb72edff0d8990293cb4ea4ece677088de10731f9c71f74dde4d140ac)
BibTeX
@misc{dcd1c28ddf561e,
  title = {RegRet: Enhancing Region-Level Retrieval in Large Multimodal Models — arXiv:2609.16847},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16847},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d1c28ddf561e; sha256 21fc2fabb72edff0d8990293cb4ea4ece677088de10731f9c71f74dde4d140ac},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16847. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Region-level retrieval aims to align user-specified image regions with relevant regions or textual descriptions, playing a crucial role in realworld applications such as e-commerce product search and RAG. Although recent Large Multimodal Models (LMMs) have made significant strides in multimodal retrieval, they primarily focus on global-level tasks and struggle to capture effective region-level representations. To bridge this gap, we present RegRet, an LMM-based Region-level Retrieval framework that enhances the regional representations without compromising overall global retrieval performance. At its core, RegRet integrates a Region-Aware Encoder to capture detailed regional features while balancing them with the global background context. To further enhance the fine-grained understanding and discriminability of representations, we design a multi-stage training pipeline that includes detailed localized captioning and regional contrastive learning tasks. In addition, considering the absence of region-level contrastive training data and the limited diversity of evaluation tasks in current benchmarks, we introduce the REGMB benchmark. It comprises 225k contrastive pairs, covering four multimodal retrieval tasks. Extensive experiments validate the effectiveness of our approach. RegRet outperforms strong baselines in the zero-shot setting. Further training with contrastive learning leads to an average improvement of more than 20\% on both REGMB and public benchmarks, while achieving comparable or better results on global-level retrieval tasks.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.16847 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T18:03:09.696Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).