EUVIMEDEUVIMED entdecken
Crossref

Discriminative and Robust Attribute Alignment for Zero-Shot Learning

De Cheng, Gerong Wang, Nannan Wang, Dingwen Zhang, Qiang Zhang, Xinbo Gao

IEEE Transactions on Circuits and Systems for Video Technology · 2023-08 · 33 (8) · 4244-4256

DOI: 10.1109/tcsvt.2023.3243205 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2023-08. Verfasst von De Cheng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 83 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Technology Innovation Leading Program of Shaanxi.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Zero-shot learning (ZSL) aims to learn models that can recognize images of semantically related unseen categories, through transferring attribute-based knowledge learned from training data of seen classes to unseen testing data. As visual attributes play a vital role in ZSL, recent embedding-based methods usually focus on learning a compatibility function between the visual representation and the class semantic attributes. While in this work, in addition to simply learning the region embedding of different semantic attributes to maintain the generalization capability of the learned model, we further consider to improve the discrimination power of the learned visual features themselves by contrastive embedding. It exploits both the class-wise and instance-wise supervision for GZSL, under the attribute guided weakly supervised representation learning framework. To further improve the robustness of the ZSL model, we also propose to train the model under the consistency regularization constraint, through taking full advantages of self-supervised signals of the image under various perturbed augmentation situations, which could make the model robust to some occluded or un-related attribute regions. Extensive experimental results demonstrate the effectiveness of the proposed ZSL method, achieving superior performances to state-of-the-art methods on three widely-used benchmark datasets, namely CUB, SUN, and AWA2. Our source code is released at https://github.com/KORIYN/CC-ZSL.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Technology Innovation Leading Program of Shaanxi
  • Open Research Projects of Zhejiang Lab

Zitieren

APA

Cheng, D., Wang, G., Wang, N., Zhang, D., Zhang, Q., & Gao, X. (2023). Discriminative and Robust Attribute Alignment for Zero-Shot Learning. IEEE Transactions on Circuits and Systems for Video Technology, 33(8), 4244-4256. https://doi.org/10.1109/tcsvt.2023.3243205

Vancouver

Cheng D, Wang G, Wang N, Zhang D, Zhang Q, Gao X. Discriminative and Robust Attribute Alignment for Zero-Shot Learning. IEEE Transactions on Circuits and Systems for Video Technology. 2023;33(8):4244-4256. doi:10.1109/tcsvt.2023.3243205

BibTeX
@article{Cheng2023,
  author = {Cheng, De and Wang, Gerong and Wang, Nannan and Zhang, Dingwen and Zhang, Qiang and Gao, Xinbo},
  title = {Discriminative and Robust Attribute Alignment for Zero-Shot Learning},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2023},
  volume = {33},
  number = {8},
  pages = {4244--4256},
  doi = {10.1109/tcsvt.2023.3243205}
}
Kostenlos starten →