Sökning: onr:"swepub:oai:research.chalmers.se:3f86bde2-e304-4c48-9882-389fb593c193" >
Joint Energy-based ...
-
Liu, Xixi,1995Chalmers tekniska högskola,Chalmers University of Technology
(författare)
Joint Energy-based Model for Deep Probabilistic Regression
- Artikel/kapitelEngelska2022
Förlag, utgivningsår, omfång ...
Nummerbeteckningar
-
LIBRIS-ID:oai:research.chalmers.se:3f86bde2-e304-4c48-9882-389fb593c193
-
ISBN:9781665490627
-
https://research.chalmers.se/publication/530089URI
-
https://doi.org/10.1109/ICPR56361.2022.9955636DOI
Kompletterande språkuppgifter
-
Språk:engelska
-
Sammanfattning på:engelska
Ingår i deldatabas
Klassifikation
-
Ämneskategori:kon swepub-publicationtype
-
Ämneskategori:ref swepub-contenttype
Anmärkningar
-
It is desirable that a deep neural network trained on a regression task does not only achieve high prediction accuracy, but its prediction posteriors are also well-calibrated, especially in safety-critical settings. Recently, energy-based models specifically to enrich regression posteriors have been proposed and achieve state-of-art results in object detection tasks. However, applying these models at prediction time is not straightforward as the resulting inference methods require to minimize an underlying energy function. Furthermore, these methods empirically do not provide accurate prediction uncertainties. Inspired by recent joint energy-based models for classification, in this work we propose to utilize a joint energy model for regression tasks and describe architectural differences needed in this setting. Within this frame-work, we apply our methods to three computer vision regression tasks. We demonstrate that joint energy-based models for deep probabilistic regression improve the calibration property, do not require expensive inference, and yield competitive accuracy in terms of the mean absolute error (MAE).
Ämnesord och genrebeteckningar
Biuppslag (personer, institutioner, konferenser, titlar ...)
-
Lin, Che-Tsung,1979Chalmers tekniska högskola,Chalmers University of Technology(Swepub:cth)chetsung
(författare)
-
Zach, Christopher,1974Chalmers tekniska högskola,Chalmers University of Technology(Swepub:cth)zach
(författare)
-
Chalmers tekniska högskola
(creator_code:org_t)
Sammanhörande titlar
-
Ingår i:Proceedings - International Conference on Pattern Recognition2022-August, s. 2693-26991051-46519781665490627
Internetlänk
Hitta via bibliotek
Till lärosätets databas