Metraipolis › archive › dc_db9568575ed7

Flow-CLIP: Image-Conditioned Residual Scoring for CompositionalImage-Text Matching — arXiv:2610.21937

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21937
License (as archived)
CC0-1.0
Archived
2026-10-16T10:35:32.758Z
SHA-256 of the archived text
5daf3196d300ab571d883f3004023925b9e27cf6f562cce02ae0ebf1a9abe21f
Stable URL of this page
https://metraipolis.com/documento/dc_db9568575ed7

How to cite

Flow-CLIP: Image-Conditioned Residual Scoring for CompositionalImage-Text Matching — arXiv:2610.21937 — arXiv (en), https://arxiv.org/abs/2610.21937 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db9568575ed7 (Metraipolis archive dc_db9568575ed7, sha256 5daf3196d300ab571d883f3004023925b9e27cf6f562cce02ae0ebf1a9abe21f)
BibTeX
@misc{dcdb9568575ed7,
  title = {Flow-CLIP: Image-Conditioned Residual Scoring for CompositionalImage-Text Matching — arXiv:2610.21937},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21937},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db9568575ed7; sha256 5daf3196d300ab571d883f3004023925b9e27cf6f562cce02ae0ebf1a9abe21f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21937. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision--language pre-training has enabled substantial progress in image--text retrieval and zero-shot recognition by learning transferable cross-modal representations. However, sentence-level alignment remains insufficient for compositional matching, where captions can describe the same objects and attributes while differing in how these elements are bound. To address this limitation, we propose Flow-CLIP, which refines global image-text alignment through image-conditioned changes in token--patch evidence. Global Compatibility Calibration (GCC) learns a sentence-level similarity metric, while Image-Conditioned Evidence Refinement (ICER) incorporates visual patch context into token queries and uses the resulting change in local matching evidence to adjust the global score. We further introduce Cross-Image Margin Ranking (CIMR), which compares the same positive--negative caption pair across matched and mismatched images, encouraging a larger ranking margin when the image supports the correct description. Experiments on compositional matching and attribute--object binding benchmarks show that Flow-CLIP improves binding accuracy over pretrained CLIP and learned global alignment through local evidence refinement, while cross-image ranking supervision mitigates reliance on language priors. Code will be released at link.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.21937 — 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 2026-10-16T08:52:02.707Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).