EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing Fashion Retrieval with Constraint Verification

Tina Aminian, Jessica Chen

Algorithms · 06.06.2026 · 19 (6) · 462

DOI: 10.3390/a19060462 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Algorithms, online erschienen am 06.06.2026. Verfasst von Tina Aminian und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Windsor Professional Development Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Composed Image Retrieval (CIR) aims to search a target database for images that best align with a user’s intent, conditioned on a reference image paired with modification requirements. Existing CIR architectures typically treat the visual reference and the textual modification as symmetrical inputs, fusing their features into a shared latent embedding space. From a user-centric perspective, however, these multi-modal inputs serve fundamentally asymmetric roles: the reference image acts as a soft semantic anchor, whereas the modification text functions as an explicit requirement specifying precise visual changes. Because current models optimize composition predominantly at a global representation level, these non-negotiable logical constraints are frequently violated during inference, leading to retrieval results that fail to satisfy the user’s explicit instructions. To mitigate this limitation, we introduce a novel, training-free verification framework for fashion retrieval that enforces textual constraint adherence without sacrificing the expressive flexibility of open-vocabulary natural language. Our approach leverages schema-conditioned large language models to extract explicit, structured logical constraints from raw queries during post-processing. A downstream vision-language agent subsequently verifies these constraints against the top retrieved candidate pool to penalize non-compliant images and optimize candidate ordering. Extensive evaluations across standard fashion benchmarks demonstrate that our plug-in framework consistently and significantly enhances the recall metrics of state-of-the-art supervised and zero-shot CIR baselines.

Förderung

  • University of Windsor Professional Development Fund

Zitieren

APA

Aminian, T., & Chen, J. (2026). Enhancing Fashion Retrieval with Constraint Verification. Algorithms, 19(6), 462. https://doi.org/10.3390/a19060462

Vancouver

Aminian T, Chen J. Enhancing Fashion Retrieval with Constraint Verification. Algorithms. 2026;19(6):462. doi:10.3390/a19060462

BibTeX
@article{Aminian2026,
  author = {Aminian, Tina and Chen, Jessica},
  title = {Enhancing Fashion Retrieval with Constraint Verification},
  journal = {Algorithms},
  year = {2026},
  volume = {19},
  number = {6},
  pages = {462},
  doi = {10.3390/a19060462}
}
Kostenlos starten →