EUVIMEDEUVIMED entdecken
Crossref

Modality Fused Class-Proxy With Knowledge Distillation for Zero-Shot Sketch-Based Image Retrieval

Chang-Xing Li, Donglin Zhang, Zhikai Hu, Xiao-Jun Wu

IEEE Transactions on Circuits and Systems for Video Technology · 2025-06 · 35 (6) · 6158-6169

DOI: 10.1109/tcsvt.2025.3530248 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-06. Verfasst von Chang-Xing Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, zero-shot sketch-based image retrieval (ZS-SBIR) task has attracted considerable attention. Although some ZS-SBIR approaches have been proposed, it remains challenging to handle the inherent linkages between the sketch and image domains. Moreover, how to transfer semantic knowledge from seen categories to unseen categories is still an open problem, significantly affecting retrieval performance. In this article, we propose a novel approach Modality Fused Class-Proxy with Knowledge Distillation, named MFCPKD, which develops two novel schemes to remedy the above issues. Specifically, MFCPKD leverages a Modality Fusion Model to learn modality-fused feature embeddings and class proxies. The knowledge distillation is employed for student to learn the feature from seen categories and infer the unknown category through class proxies. Furthermore, three losses constrain the student network to narrow the modality gap between sketch and image domains. Finally, we conduct extensive experiments on three benchmark datasets (Sketchy Ext, TU-Berlin Ext, and QuickDraw Ext) and demonstrate that our MFCPKD method can achieve excellent performance compared to some existing methods in ZS-SBIR scenarios. The code for our project is available at https://github.com/li1changxing/MFCPKD.

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities
  • National Key Research and Development Program of China

Zitieren

APA

Li, C., Zhang, D., Hu, Z., & Wu, X. (2025). Modality Fused Class-Proxy With Knowledge Distillation for Zero-Shot Sketch-Based Image Retrieval. IEEE Transactions on Circuits and Systems for Video Technology, 35(6), 6158-6169. https://doi.org/10.1109/tcsvt.2025.3530248

Vancouver

Li C, Zhang D, Hu Z, Wu X. Modality Fused Class-Proxy With Knowledge Distillation for Zero-Shot Sketch-Based Image Retrieval. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(6):6158-6169. doi:10.1109/tcsvt.2025.3530248

BibTeX
@article{Li2025,
  author = {Li, Chang-Xing and Zhang, Donglin and Hu, Zhikai and Wu, Xiao-Jun},
  title = {Modality Fused Class-Proxy With Knowledge Distillation for Zero-Shot Sketch-Based Image Retrieval},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2025},
  volume = {35},
  number = {6},
  pages = {6158--6169},
  doi = {10.1109/tcsvt.2025.3530248}
}
Kostenlos starten →