EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Recovering manifold representations via unsupervised meta-learning

Yunye Gong, Jiachen Yao, Ruyi Lian, Xiao Lin, Chao Chen, Ajay Divakaran, Yi Yao

Frontiers in Computer Science · 15.01.2025 · 6

DOI: 10.3389/fcomp.2024.1255517 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Computer Science, online erschienen am 15.01.2025. Verfasst von Yunye Gong und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Defense Sciences Office, DARPA.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Manifold representation learning holds great promise for theoretical understanding and characterization of deep neural networks' behaviors through the lens of geometries. However, data scarcity remains a major challenge in manifold analysis especially for data and applications with real-world complexity. To address this issue, we propose manifold representation meta-learning (MRML) based on autoencoders to recover the underlying manifold structures without uniformly or densely sampled data. Specifically, we adopt episodic training, following model agnostic meta-learning, to meta-learn autoencoders that are generalizable to unseen samples specifically corresponding to regions with low-sampling density. We demonstrate the effectiveness of MRML via empirical experiments on LineMOD, a dataset curated for 6-D object pose estimation. We also apply topological metrics based on persistent homology and neighborhood graphs for quantitative assessment of manifolds reconstructed by MRML. In comparison to state-of-the-art baselines, our proposed approach demonstrates improved manifold reconstruction better matching the data manifold by preserving prominent topological features and relative proximity of samples.

Förderung

  • Defense Sciences Office, DARPA

Zitieren

APA

Gong, Y., Yao, J., Lian, R., Lin, X., Chen, C., Divakaran, A., & Yao, Y. (2025). Recovering manifold representations via unsupervised meta-learning. Frontiers in Computer Science, 6. https://doi.org/10.3389/fcomp.2024.1255517

Vancouver

Gong Y, Yao J, Lian R, Lin X, Chen C, Divakaran A, et al. Recovering manifold representations via unsupervised meta-learning. Frontiers in Computer Science. 2025;6. doi:10.3389/fcomp.2024.1255517

BibTeX
@article{Gong2025,
  author = {Gong, Yunye and Yao, Jiachen and Lian, Ruyi and Lin, Xiao and Chen, Chao and Divakaran, Ajay and Yao, Yi},
  title = {Recovering manifold representations via unsupervised meta-learning},
  journal = {Frontiers in Computer Science},
  year = {2025},
  volume = {6},
  doi = {10.3389/fcomp.2024.1255517}
}
Kostenlos starten →