Timezone: »

 
Poster
On the Practicality of Deterministic Epistemic Uncertainty
Janis Postels · Mattia Segù · Tao Sun · Luca Daniel Sieber · Luc Van Gool · Fisher Yu · Federico Tombari

Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #506

A set of novel approaches for estimating epistemic uncertainty in deep neural networks with a single forward pass has recently emerged as a valid alternative to Bayesian Neural Networks. On the premise of informative representations, these deterministic uncertainty methods (DUMs) achieve strong performance on detecting out-of-distribution (OOD) data while adding negligible computational costs at inference time. However, it remains unclear whether DUMs are well calibrated and can seamlessly scale to real-world applications - both prerequisites for their practical deployment. To this end, we first provide a taxonomy of DUMs, and evaluate their calibration under continuous distributional shifts. Then, we extend them to semantic segmentation. We find that, while DUMs scale to realistic vision tasks and perform well on OOD detection, the practicality of current methods is undermined by poor calibration under distributional shifts.

Author Information

Janis Postels (ETH Zurich)
Mattia Segù (ETH Zurich)
Tao Sun (ETH Zurich)
Luca Daniel Sieber (ETH Zurich)
Luc Van Gool (ETH Zurich)
Fisher Yu (ETH Zurich)
Federico Tombari (Google, TU Munich)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors

  • 2023 Poster: BiBench: Benchmarking and Analyzing Network Binarization »
    Haotong Qin · Mingyuan Zhang · Yifu Ding · Aoyu Li · Zhongang Cai · Ziwei Liu · Fisher Yu · Xianglong Liu
  • 2023 Poster: Scaling Vision Transformers to 22 Billion Parameters »
    Mostafa Dehghani · Josip Djolonga · Basil Mustafa · Piotr Padlewski · Jonathan Heek · Justin Gilmer · Andreas Steiner · Mathilde Caron · Robert Geirhos · Ibrahim Alabdulmohsin · Rodolphe Jenatton · Lucas Beyer · Michael Tschannen · Anurag Arnab · Xiao Wang · Carlos Riquelme · Matthias Minderer · Joan Puigcerver · Utku Evci · Manoj Kumar · Sjoerd van Steenkiste · Gamaleldin Elsayed · Aravindh Mahendran · Fisher Yu · Avital Oliver · Fantine Huot · Jasmijn Bastings · Mark Collier · Alexey Gritsenko · Vighnesh N Birodkar · Cristina Vasconcelos · Yi Tay · Thomas Mensink · Alexander Kolesnikov · Filip Pavetic · Dustin Tran · Thomas Kipf · Mario Lucic · Xiaohua Zhai · Daniel Keysers · Jeremiah Harmsen · Neil Houlsby
  • 2023 Oral: Scaling Vision Transformers to 22 Billion Parameters »
    Mostafa Dehghani · Josip Djolonga · Basil Mustafa · Piotr Padlewski · Jonathan Heek · Justin Gilmer · Andreas Steiner · Mathilde Caron · Robert Geirhos · Ibrahim Alabdulmohsin · Rodolphe Jenatton · Lucas Beyer · Michael Tschannen · Anurag Arnab · Xiao Wang · Carlos Riquelme · Matthias Minderer · Joan Puigcerver · Utku Evci · Manoj Kumar · Sjoerd van Steenkiste · Gamaleldin Elsayed · Aravindh Mahendran · Fisher Yu · Avital Oliver · Fantine Huot · Jasmijn Bastings · Mark Collier · Alexey Gritsenko · Vighnesh N Birodkar · Cristina Vasconcelos · Yi Tay · Thomas Mensink · Alexander Kolesnikov · Filip Pavetic · Dustin Tran · Thomas Kipf · Mario Lucic · Xiaohua Zhai · Daniel Keysers · Jeremiah Harmsen · Neil Houlsby
  • 2022 Poster: Flow-Guided Sparse Transformer for Video Deblurring »
    Jing Lin · Yuanhao Cai · Xiaowan Hu · Haoqian Wang · Youliang Yan · Xueyi Zou · Henghui Ding · Yulun Zhang · Radu Timofte · Luc Van Gool
  • 2022 Spotlight: Flow-Guided Sparse Transformer for Video Deblurring »
    Jing Lin · Yuanhao Cai · Xiaowan Hu · Haoqian Wang · Youliang Yan · Xueyi Zou · Henghui Ding · Yulun Zhang · Radu Timofte · Luc Van Gool
  • 2022 Poster: Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration »
    Jing Lin · Xiaowan Hu · Yuanhao Cai · Haoqian Wang · Youliang Yan · Xueyi Zou · Yulun Zhang · Luc Van Gool
  • 2022 Spotlight: Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration »
    Jing Lin · Xiaowan Hu · Yuanhao Cai · Haoqian Wang · Youliang Yan · Xueyi Zou · Yulun Zhang · Luc Van Gool
  • 2020 Poster: T-Basis: a Compact Representation for Neural Networks »
    Anton Obukhov · Maxim Rakhuba · Stamatios Georgoulis · Menelaos Kanakis · Dengxin Dai · Luc Van Gool
  • 2020 Poster: Frustratingly Simple Few-Shot Object Detection »
    Xin Wang · Thomas Huang · Joseph E Gonzalez · Trevor Darrell · Fisher Yu
  • 2019 : Fisher Yu: "Motion and Prediction for Autonomous Driving" »
    Fisher Yu · Trevor Darrell