EUVIMEDEUVIMED entdecken
Crossref

Dual Adversarial Perturbations for Zero-Shot Learning

Lei Wang, Shiming Chen, Guo-Sen Xie, Chaojian Yu, Xinhua You, Qinmu Peng, Xinge You

IEEE Transactions on Circuits and Systems for Video Technology · 2026-08 · 36 (8) · 12504-12516

DOI: 10.1109/tcsvt.2026.3679600 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-08. Verfasst von Lei Wang und 6 weiteren Autor:innen. Die Arbeit nennt 89 Literaturangaben. Gefördert von: Fundamental Research Funds for the Central Universities, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In Zero-Shot Learning (ZSL), embedding-based methods learn a visual–semantic mapping that leverages the attribute knowledge of seen classes to predict the attributes of unseen classes, enabling knowledge transfer from seen to unseen classes. However, distributional discrepancies between seen and unseen classes introduce an inherent domain shift, and inter-class variations cause the same attribute to be expressed differently across categories. As a result, models trained on seen classes often struggle to accurately recognize attributes in unseen classes, limiting their generalization ability. To address these challenges, we propose DAPZSL, a dual adversarial perturbation framework that enhances the robustness of visual–semantic mappings through Feature-Level Adversarial Perturbation (FAP) and improves the model’s generalization ability via Weight-Level Adversarial Perturbation (WAP). Specifically, FAP generates semantically perturbed adversarial samples at the feature level, and incorporating these samples during training encourages the model to learn more robust visual–semantic mappings that are resilient to semantic variations, which improves attribute recognition on unseen classes. Meanwhile, WAP introduces adversarial perturbations into the model’s weight space, promoting a flatter loss landscape that alleviates overfitting to seen classes and enhances generalization. Extensive experiments on multiple benchmark datasets—including AWA2, SUN, and CUB—demonstrate that DAPZSL significantly outperforms existing ZSL models.

Förderung

  • Fundamental Research Funds for the Central Universities
  • National Natural Science Foundation of China

Zitieren

APA

Wang, L., Chen, S., Xie, G., Yu, C., You, X., Peng, Q., & You, X. (2026). Dual Adversarial Perturbations for Zero-Shot Learning. IEEE Transactions on Circuits and Systems for Video Technology, 36(8), 12504-12516. https://doi.org/10.1109/tcsvt.2026.3679600

Vancouver

Wang L, Chen S, Xie G, Yu C, You X, Peng Q, et al. Dual Adversarial Perturbations for Zero-Shot Learning. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(8):12504-12516. doi:10.1109/tcsvt.2026.3679600

BibTeX
@article{Wang2026,
  author = {Wang, Lei and Chen, Shiming and Xie, Guo-Sen and Yu, Chaojian and You, Xinhua and Peng, Qinmu and You, Xinge},
  title = {Dual Adversarial Perturbations for Zero-Shot Learning},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2026},
  volume = {36},
  number = {8},
  pages = {12504--12516},
  doi = {10.1109/tcsvt.2026.3679600}
}
Kostenlos starten →