Joint Energy-based Model for Deep Probabilistic Regression

Liu, Xixi,1995Chalmers tekniska högskola,Chalmers University of Technology (author)

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).

Lin, Che-Tsung,1979Chalmers tekniska högskola,Chalmers University of Technology(Swepub:cth)chetsung (author)
Zach, Christopher,1974Chalmers tekniska högskola,Chalmers University of Technology(Swepub:cth)zach (author)
Chalmers tekniska högskola (creator_code:org_t)

In:Proceedings - International Conference on Pattern Recognition2022-August, s. 2693-26991051-46519781665490627

By the author/editor: Liu, Xixi, 1995; Lin, Che-Tsung, ...; Zach, Christophe ...

About the subject

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...; and Computer Vision ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.