EUVIMEDEUVIMED entdecken
Crossref

Few-Shot Partial Multi-View Learning

Yuan Zhou, Yanrong Guo, Shijie Hao, Richang Hong, Jiebo Luo

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023-10 · 45 (10) · 11824-11841

DOI: 10.1109/tpami.2023.3275162 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023-10. Verfasst von Yuan Zhou und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 74 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

It is often the case that data are with multiple views in real-world applications. Fully exploring the information of each view is significant for making data more representative. However, due to various limitations and failures in data collection and pre-processing, it is inevitable for real data to suffer from view missing and data scarcity. The coexistence of these two issues makes it more challenging to achieve the pattern classification task. Currently, to our best knowledge, few appropriate methods can well-handle these two issues simultaneously. Aiming to draw more attention from the community to this challenge, we propose a new task in this paper, called few-shot partial multi-view learning, which focuses on overcoming the negative impact of the view-missing issue in the low-data regime. The challenges of this task are twofold: (i) it is difficult to overcome the impact of data scarcity under the interference of missing views; (ii) the limited number of data exacerbates information scarcity, thus making it harder to address the view-missing issue in turn. To address these challenges, we propose a new unified Gaussian dense-anchoring method. The unified dense anchors are learned for the limited partial multi-view data, thereby anchoring them into a unified dense representation space where the influence of data scarcity and view missing can be alleviated. We conduct extensive experiments to evaluate our method. The results on Cub-googlenet-doc2vec, Handwritten, Caltech102, Scene15, Animal, ORL, tieredImagenet, and Birds-200-2011 datasets validate its effectiveness. The codes will be released at https://github.com/zhouyuan888888/UGDA.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China

Zitieren

APA

Zhou, Y., Guo, Y., Hao, S., Hong, R., & Luo, J. (2023). Few-Shot Partial Multi-View Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(10), 11824-11841. https://doi.org/10.1109/tpami.2023.3275162

Vancouver

Zhou Y, Guo Y, Hao S, Hong R, Luo J. Few-Shot Partial Multi-View Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(10):11824-11841. doi:10.1109/tpami.2023.3275162

BibTeX
@article{Zhou2023,
  author = {Zhou, Yuan and Guo, Yanrong and Hao, Shijie and Hong, Richang and Luo, Jiebo},
  title = {Few-Shot Partial Multi-View Learning},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2023},
  volume = {45},
  number = {10},
  pages = {11824--11841},
  doi = {10.1109/tpami.2023.3275162}
}
Kostenlos starten →