EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Zero-Shot Clothing Sketch Retrieval and Feature Alignment Based on CLIP Contrastive Learning

Sophie Bernard, Jean Dupont

American Journal of Artificial Intelligence and Neural Networks · 28.02.2026 · 7 (1) · 95-107

DOI: 10.71465/ajainn3590 ↗

Kurz gefasst

Fachartikel in der Zeitschrift American Journal of Artificial Intelligence and Neural Networks, online erschienen am 28.02.2026. Verfasst von Sophie Bernard und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid expansion of e-commerce platforms has necessitated the development of advanced information retrieval systems that allow users to search for products using intuitive modalities. Sketch-based image retrieval (SBIR) has emerged as a critical research area, bridging the domain gap between abstract, hand-drawn sketches and realistic product photographs. However, traditional SBIR methods often rely on closed-set assumptions, where the training and testing categories overlap completely. This presents a significant limitation in real-world scenarios where new fashion trends and clothing categories emerge constantly. This paper addresses the challenge of Zero-Shot SBIR (ZS-SBIR) within the clothing domain by leveraging the semantic power of Contrastive Language-Image Pre-training (CLIP). We propose a novel feature alignment framework that utilizes CLIP as a backbone to extractrobust semantic representations. By introducing a specializedprojection module and a semantic consistency regularization mechanism, we effectively align the disparate visual features of sketches and photos within a shared embedding space. Our approach mitigates the domain shift problem and preserves semantic integrity for unseen categories. Extensive experiments on standard benchmark datasets demonstrate that our method significantly outperforms state-of-the-art approaches in zero-shot retrieval tasks. The results validate the efficacy of contrastive learning in harmonizing cross-modal features and establish a new baseline for sketch-based clothing retrieval.

Zitieren

APA

Bernard, S., & Dupont, J. (2026). Zero-Shot Clothing Sketch Retrieval and Feature Alignment Based on CLIP Contrastive Learning. American Journal of Artificial Intelligence and Neural Networks, 7(1), 95-107. https://doi.org/10.71465/ajainn3590

Vancouver

Bernard S, Dupont J. Zero-Shot Clothing Sketch Retrieval and Feature Alignment Based on CLIP Contrastive Learning. American Journal of Artificial Intelligence and Neural Networks. 2026;7(1):95-107. doi:10.71465/ajainn3590

BibTeX
@article{Bernard2026,
  author = {Bernard, Sophie and Dupont, Jean},
  title = {Zero-Shot Clothing Sketch Retrieval and Feature Alignment Based on CLIP Contrastive Learning},
  journal = {American Journal of Artificial Intelligence and Neural Networks},
  year = {2026},
  volume = {7},
  number = {1},
  pages = {95--107},
  doi = {10.71465/ajainn3590}
}
Kostenlos starten →