Metraipolis › archive › dc_7bcd6c94d3d0

DeCo: Efficient Decouple-to-Couple Learning for Multi-Task Visual Grounding — arXiv:2609.24409

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24409
License (as archived)
CC0-1.0
Archived
2026-10-09T22:05:50.361Z
SHA-256 of the archived text
58663f31386e2323828893b8d58b77474ec4bc981fedf5dad26fe34021f8eec1
Stable URL of this page
https://metraipolis.com/documento/dc_7bcd6c94d3d0

How to cite

DeCo: Efficient Decouple-to-Couple Learning for Multi-Task Visual Grounding — arXiv:2609.24409 — arXiv (en), https://arxiv.org/abs/2609.24409 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7bcd6c94d3d0 (Metraipolis archive dc_7bcd6c94d3d0, sha256 58663f31386e2323828893b8d58b77474ec4bc981fedf5dad26fe34021f8eec1)
BibTeX
@misc{dc7bcd6c94d3d0,
  title = {DeCo: Efficient Decouple-to-Couple Learning for Multi-Task Visual Grounding — arXiv:2609.24409},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24409},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7bcd6c94d3d0; sha256 58663f31386e2323828893b8d58b77474ec4bc981fedf5dad26fe34021f8eec1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24409. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-task visual grounding requires models to jointly understand linguistic semantics and perform accurate visual localization and segmentation. Despite the success of multimodal large language models, effectively adapting them to multiple grounding objectives remains challenging. Existing methods commonly enforce task cooperation through shared representations, while overlooking the intrinsic conflict between task-oriented feature interests. In this paper, we introduce $\textbf{DeCo}$, an efficient $\textbf{De}$couple-to-$\textbf{Co}$uple learning framework that resolves this dilemma through a two-stage paradigm: task-specific representation decoupling followed by complementary prior coupling. Specifically, we first propose Task-aware Semantic Decoupling (TSD) to route shared visual cues into individual features under salient word-level guidance, alleviating representation interference between localization and segmentation. Furthermore, we observe that segmentation naturally provides informative localization priors due to dense supervision. Based on this insight, we introduce Hybrid Prior Coupling (HPC), which integrates sentence-level semantic prior with mask-derived spatial prior for enhanced grounding. Built upon a frozen multimodal encoder, DeCo requires lightweight trainable parameters while achieving strong generalization across multiple grounding objectives. Extensive experiments on RefCOCO/+, G-Ref, ReferIt, Flickr, DIOR-RSVG, SARVG1.0, RRSIS-D, RIS-LAD, and RefDIOR demonstrate that DeCo achieves state-of-the-art performance on both natural and remote sensing benchmarks. The code and models are available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.24409 — 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 2026-10-09T21:45:21.036Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).