Metraipolis › archive › dc_80417aaf6ca4
RA-CoA: Training-free Fashion Image Captioning via Retrieval-Augmented Chain-of-Attributes — arXiv:2609.14100
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.14100
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T22:50:52.399Z
- SHA-256 of the archived text
8f797a127eb24cb36fc0a0aeacbb9b80891265f43626013223c385f9d150a299- Stable URL of this page
https://metraipolis.com/documento/dc_80417aaf6ca4
How to cite
RA-CoA: Training-free Fashion Image Captioning via Retrieval-Augmented Chain-of-Attributes — arXiv:2609.14100 — arXiv (en), https://arxiv.org/abs/2609.14100 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_80417aaf6ca4 (Metraipolis archive dc_80417aaf6ca4, sha256 8f797a127eb24cb36fc0a0aeacbb9b80891265f43626013223c385f9d150a299)
BibTeX
@misc{dc80417aaf6ca4,
title = {RA-CoA: Training-free Fashion Image Captioning via Retrieval-Augmented Chain-of-Attributes — arXiv:2609.14100},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.14100},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_80417aaf6ca4; sha256 8f797a127eb24cb36fc0a0aeacbb9b80891265f43626013223c385f9d150a299},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14100. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Fashion Image Captioning (FIC) plays a vital role in enhancing user experience and product search in e-commerce platforms. Unlike natural scene image captioning, FIC requires fine-grained visual reasoning and knowledge of domain-specific terminology to capture subtle attributes such as neckline and closure types, graphic patterns, and dress silhouettes. Moreover, as fashion inventories evolve rapidly with new trends, styles, and frequently emerging vocabulary, developing training-free captioning solution becomes essential for scalability and real-world adaptability. Instruction-tuned vision-language models (VLMs) offer a promising solution to fashion image captioning dueto their strong zero-shot capabilities and natural language fluency. However, these general-purpose models often lack attribute-level coverage and precision, and tend to hallucinate or misidentify fine-grained fashion details, making them less suitable for high-fidelity applications like product cataloging or personalized recommendations. To address this, we propose RA-CoA (Retrieval-Augmented Chain-of-Attributes), a novel, training-free framework that disentangles fashion image captioning into two interpretable stages: (i) retrieval of relevant attribute sets from a product knowledge base, and (ii) attribute-level reasoning to generate the final caption. RA-CoA is a model-agnostic approach that works with frozen VLMs to improve fine-grained attribute precision in product captions without the need for fine-tuning. Extensive evaluations across diverse VLM model families under different prompting paradigms demonstrate that RA-CoA significantly improves caption quality, achieving an average gain of 26.3% METEOR score over zero-shot captioning. We make our code publicly available. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.14100 — 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 2026-10-15T22:29:03.617Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).