paper-with-me

Papers

Discriminant Distance-Aware Representation on Deterministic Uncertainty Quantification Methods

2024-02-20 · Jiaxin Zhang, Kamalika Das, Sricharan Kumar

Uncertainty estimation is a crucial aspect of deploying dependable deep learning models in safety-critical systems. In this study, we introduce a novel and efficient method for deterministic uncertainty estimation called Discriminant Distance-Awareness Representation (DDAR). Our approach involves constructing a DNN model that incorporates a set of prototypes in its latent representations, enabling us to analyze valuable feature information from the input data. By leveraging a distinction maximization layer over optimal trainable prototypes, DDAR can learn a discriminant distance-awareness representation. We demonstrate that DDAR overcomes feature collapse by relaxing the Lipschitz constraint that hinders the practicality of deterministic uncertainty methods (DUMs) architectures. Our experiments show that DDAR is a flexible and architecture-agnostic method that can be easily integrated as a pluggable layer with distance-sensitive metrics, outperforming state-of-the-art uncertainty estimation methods on multiple benchmark problems.

📄 PDF Abstract BibTeX arXiv:2402.12664

Code (0)

등록된 구현이 없습니다.

Tasks

Uncertainty Quantification

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Latent Discriminant deterministic Uncertainty

2022-07-20 · Gianni Franchi, Xuanlong Yu, Andrei Bursuc, Emanuel Aldea 외

Predictive uncertainty estimation is essential for deploying Deep Neural Networks in real-world autonomous systems. However, most successful approaches are computationally intensive. In this work, we attempt to address t…

Autonomous DrivingDepth Estimationimage-classificationImage Classification+3

A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness

2022-05-01 · Jeremiah Zhe Liu, Shreyas Padhy, Jie Ren, Zi Lin 외

Accurate uncertainty quantification is a major challenge in deep learning, as neural networks can make overconfident errors and assign high confidence predictions to out-of-distribution (OOD) inputs. The most popular app…

Data AugmentationDeep LearningProbabilistic Deep LearningUncertainty Quantification

Stochastic Vision Transformers with Wasserstein Distance-Aware Attention

2023-11-30 · Franciskus Xaverius Erick, Mina Rezaei, Johanna Paula Müller, Bernhard Kainz

Self-supervised learning is one of the most promising approaches to acquiring knowledge from limited labeled data. Despite the substantial advancements made in recent years, self-supervised models have posed a challenge …

Out-of-Distribution DetectionSelf-Supervised LearningTransfer Learning

Deep Deterministic Uncertainty: A Simple Baseline

2021-02-23 · Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort, Philip H. S. Torr 외

Reliable uncertainty from deterministic single-forward pass models is sought after because conventional methods of uncertainty quantification are computationally expensive. We take two complex single-forward-pass uncerta…

Active LearningUncertainty Quantification

Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness

2020-06-17 · NeurIPS 2020 12 · Jeremiah Zhe Liu, Zi Lin, Shreyas Padhy, Dustin Tran 외

Bayesian neural networks (BNN) and deep ensembles are principled approaches to estimate the predictive uncertainty of a deep learning model. However their practicality in real-time, industrial-scale applications are limi…

Uncertainty Quantification