What uncertainties do we need in Bayesian deep learning for computer vision?

Conference item

There are two major types of uncertainty one can model. Aleatoric uncertainty captures noise inherent in the observations. On the other hand, epistemic uncertainty accounts for uncertainty in the model – uncertainty which can be explained away given enough data. Traditionally it has been difficult to model epistemic uncertainty in computer vision, but with new Bayesian deep learning tools this is now possible. We study the benefits of modeling epistemic vs. aleatoric uncertainty in Bayesian deep learning models for vision tasks. For this we present a Bayesian deep learning framework combining input-dependent aleatoric uncertainty together with epistemic uncertainty. We study models under the framework with per-pixel semantic segmentation and depth regression tasks. Further, our explicit uncertainty formulation leads to new loss functions for these tasks, which can be interpreted as learned attenuation. This makes the loss more robust to noisy data, also giving new state-of-the-art results on segmentation and depth regression benchmarks.

Authors: Kendall, A; Gal, Y

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Curran Associates
• Host title: Advances in Neural Information Processing Systems 30: 31st Annual Conference on Neural Information Processing Systems (NIPS 2017)
• Volume: 30
• Pages: 5574-5584
• Publication date: 2017-12-04
• Acceptance date: 2017-09-04
• Event title: 31st Annual Conference on Neural Information Processing Systems (NIPS 2017)
• Event location: Long Beach, California, USA
• Event website: https://nips.cc/Conferences/2017
• Event start date: 2017-12-04
• Event end date: 2017-12-09
• ISBN: 9781510860964
• Language: English