Metraipolis › archive › dc_eb5fc0af889e

0.5%>100%: Bidirectional Reciprocal Learning for Referring Image Segmentation — arXiv:2609.24510

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.24510
License (as archived): CC0-1.0
Archived: 2026-10-09T22:06:06.543Z
SHA-256 of the archived text: 38b2c4566061d799181789a652a13336449af020541f30a5befe5b722c396188
Stable URL of this page: https://metraipolis.com/documento/dc_eb5fc0af889e

How to cite

0.5%>100%: Bidirectional Reciprocal Learning for Referring Image Segmentation — arXiv:2609.24510 — arXiv (en), https://arxiv.org/abs/2609.24510 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb5fc0af889e (Metraipolis archive dc_eb5fc0af889e, sha256 38b2c4566061d799181789a652a13336449af020541f30a5befe5b722c396188)

BibTeX

@misc{dceb5fc0af889e,
  title = {0.5%>100%: Bidirectional Reciprocal Learning for Referring Image Segmentation — arXiv:2609.24510},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24510},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb5fc0af889e; sha256 38b2c4566061d799181789a652a13336449af020541f30a5befe5b722c396188},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24510. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in vision foundation models (VFMs) have shown remarkable capabilities across diverse unimodal visual tasks. However, adapting VFMs to referring image segmentation (RIS) typically necessitates precise vision-language alignment via full fine-tuning, incurring substantial computational overhead and risking catastrophic forgetting. While existing parameter-efficient fine-tuning (PEFT) methods enable safe knowledge transfer with minimal training costs, they predominantly operate independently within individual modalities or focus exclusively on unidirectional guidance from language to vision, overlooking progressive cross-modal interaction and visual feedback for textual refinement. To address these limitations, we propose $\textbf{B}$idirectional $\textbf{R}$eciprocal $\textbf{L}$earning ($\textbf{BRL}$), a novel adapter-based PEFT framework that facilitates hierarchical, bidirectional information flow within both token-mixing and channel-mixing layers of frozen foundation models. Specifically, BRL introduces two complementary lightweight modules. The Reciprocal Attention Adapter (RAA) performs cross-modal query-key exchanges at the token level, enabling visual and linguistic tokens to mutually attend to each other for fine-grained spatial grounding. The Reciprocal Gate Adapter (RGA) generates cross-modal gating signals at the channel level, allowing global semantic context from one modality to adaptively recalibrate channel activations of the other. Extensive experiments on RefCOCO, RefCOCO+, and RefCOCOg benchmarks demonstrate the superiority of BRL over prior RIS methods, achieving state-of-the-art performance while requiring less than 0.5% backbone parameter updates. Code and models will be released 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/2609.24510 — 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 2026-10-09T21:45:21.052Z 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).