Uncertainty Estimation Using a Single Deep Deterministic Neural Network
By Joost R. van Amersfoort, Lewis Smith, Yee Whye Teh, Yarin Gal. 2020
560 citations recorded by the source corpus.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Sergey Levine
- Philip H. S. Torr
- Yoshua Bengio
- Ilya Kostrikov
- Trevor Darrell
- Abhinav Kumar Gupta
- Ruslan Salakhutdinov
- Andrew Zisserman
Citations in the corpus
- Offline Reinforcement Learning with Fisher Divergence Critic Regularization (2021, background): “…first popularized in machine learning by Wasserstein generative-adversarial networks (Arjovsky et al., 2017), but also used in imitation learning (Kostrikov et al., 2018), cross-domain disentan- glement (Gonzalez-Garcia et al., 2018), and uncertainty estimation (van Amersfoort et al., 2020).”
- Is Out-of-Distribution Detection Learnable? (2022, methodology): “[69] Joost Van Amersfoort, Lewis Smith, Yee Whye Teh, and Yarin Gal.”
- Out-of-distribution Detection with Deep Nearest Neighbors (2022, unknown): “…& Gales, 2018; Hendrycks et al., 2019; Geifman & El-Yaniv, 2019; Hein et al., 2019; Meinke & Hein, 2019; Mohseni et al., 2020; Liu et al., 2020; Jeong & Kim, 2020; Van Amersfoort et al., 2020; Yang et al., 2021; Chen et al., 2021; Wei et al., 2022; Ming et al., 2022a; Katz-Samuels et al., 2022).”
- Generalized Out-of-Distribution Detection: A Survey (2021, unknown): “Moreover, other works leverage distances with radial basis function kernel [177], Euclidean distance [178], and geodesic”
- Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty (2021, methodology): “As discussed in van Amersfoort et al. [2020], the lower Lipschitz bound ensures sensitivity to distances in the input space, thereby ensuring sensitivity to OoD samples.”
- Drone-Based RGB-Infrared Cross-Modality Vehicle Detection Via Uncertainty-Aware Learning (2020, unknown): “Mount efforts have been developed to quantify the uncertainty by constructing a mathematical distribution [48]–[50], which is quantified to evaluate indicators such as variance and standard deviation.”