Metraipolis › archive › dc_cd7f715de4cb

Less is More: Concise Retrieval and Critic-based Re-ranking for Composed Image Retrieval — arXiv:2610.27538

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.27538
License (as archived)
CC0-1.0
Archived
2026-10-21T07:07:50.448Z
SHA-256 of the archived text
b822c6ecc954746174075c951fd0138ec147333229e12dcac0b67f8adbcd1f6a
Stable URL of this page
https://metraipolis.com/documento/dc_cd7f715de4cb

How to cite

Less is More: Concise Retrieval and Critic-based Re-ranking for Composed Image Retrieval — arXiv:2610.27538 — arXiv (en), https://arxiv.org/abs/2610.27538 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd7f715de4cb (Metraipolis archive dc_cd7f715de4cb, sha256 b822c6ecc954746174075c951fd0138ec147333229e12dcac0b67f8adbcd1f6a)
BibTeX
@misc{dccd7f715de4cb,
  title = {Less is More: Concise Retrieval and Critic-based Re-ranking for Composed Image Retrieval — arXiv:2610.27538},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.27538},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd7f715de4cb; sha256 b822c6ecc954746174075c951fd0138ec147333229e12dcac0b67f8adbcd1f6a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27538. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image based on a reference image and modification text. Recent approaches commonly rely on large vision-language models to generate target image captions for retrieval. However, these captions may include redundant semantic details, introducing noise when retrieving the target image and leading to suboptimal retrieval results. To address this issue, we propose Less-is-More CIR, a two-stage training-free framework that combines Concise Retrieval and Critic Re-ranking. In the first stage, concise target-oriented captions are generated that preserve only the most discriminative modification semantics, thereby reducing semantic noise in the retrieval. In the second stage, a critic re-rank module further evaluates the retrieved candidates from the perspectives of modification consistency and reference preservation. Extensive experiments demonstrate the effectiveness and robustness of the proposed framework for the ZS-CIR. Our code is available at: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.27538 — 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 2026-10-21T07:05:43.570Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).