EUVIMEDEUVIMED entdecken
Crossref

Post-hoc Uncertainty Learning Using a Dirichlet Meta-Model

Maohao Shen, Yuheng Bu, Prasanna Sattigeri, Soumya Ghosh, Subhro Das, Gregory Wornell

Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (8) · 9772-9781

DOI: 10.1609/aaai.v37i8.26167 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Maohao Shen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

It is known that neural networks have the problem of being over-confident when directly using the output label distribution to generate uncertainty measures. Existing methods mainly resolve this issue by retraining the entire model to impose the uncertainty quantification capability so that the learned model can achieve desired performance in accuracy and uncertainty prediction simultaneously. However, training the model from scratch is computationally expensive, and a trade-off might exist between prediction accuracy and uncertainty quantification. To this end, we consider a more practical post-hoc uncertainty learning setting, where a well-trained base model is given, and we focus on the uncertainty quantification task at the second stage of training. We propose a novel Bayesian uncertainty learning approach using the Dirichlet meta-model, which is effective and computationally efficient. Our proposed method requires no additional training data and is flexible enough to quantify different uncertainties and easily adapt to different application settings, including out-of-domain data detection, misclassification detection, and trustworthy transfer learning. Finally, we demonstrate our proposed meta-model approach's flexibility and superior empirical performance on these applications over multiple representative image classification benchmarks.

Zitieren

APA

Shen, M., Bu, Y., Sattigeri, P., Ghosh, S., Das, S., & Wornell, G. (2023). Post-hoc Uncertainty Learning Using a Dirichlet Meta-Model. Proceedings of the AAAI Conference on Artificial Intelligence, 37(8), 9772-9781. https://doi.org/10.1609/aaai.v37i8.26167

Vancouver

Shen M, Bu Y, Sattigeri P, Ghosh S, Das S, Wornell G. Post-hoc Uncertainty Learning Using a Dirichlet Meta-Model. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(8):9772-9781. doi:10.1609/aaai.v37i8.26167

BibTeX
@article{Shen2023,
  author = {Shen, Maohao and Bu, Yuheng and Sattigeri, Prasanna and Ghosh, Soumya and Das, Subhro and Wornell, Gregory},
  title = {Post-hoc Uncertainty Learning Using a Dirichlet Meta-Model},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2023},
  volume = {37},
  number = {8},
  pages = {9772--9781},
  doi = {10.1609/aaai.v37i8.26167}
}
Kostenlos starten →