paper-with-me

Papers

Packed-Ensembles for Efficient Uncertainty Estimation

2022-10-17 · Olivier Laurent, Adrien Lafage, Enzo Tartaglione, Geoffrey Daniel, Jean-Marc Martinez, Andrei Bursuc, Gianni Franchi

Deep Ensembles (DE) are a prominent approach for achieving excellent performance on key metrics such as accuracy, calibration, uncertainty estimation, and out-of-distribution detection. However, hardware limitations of real-world systems constrain to smaller ensembles and lower-capacity networks, significantly deteriorating their performance and properties. We introduce Packed-Ensembles (PE), a strategy to design and train lightweight structured ensembles by carefully modulating the dimension of their encoding space. We leverage grouped convolutions to parallelize the ensemble into a single shared backbone and forward pass to improve training and inference speeds. PE is designed to operate within the memory limits of a standard neural network. Our extensive research indicates that PE accurately preserves the properties of DE, such as diversity, and performs equally well in terms of accuracy, calibration, out-of-distribution detection, and robustness to distribution shift. We make our code available at https://github.com/ENSTA-U2IS/torch-uncertainty.

📄 PDF Abstract BibTeX arXiv:2210.09184

Code (1)

ENSTA-U2IS-AI/torch-uncertainty 공식 구현 pytorch

Tasks

Classifier calibrationDiversityImage ClassificationOut-of-Distribution DetectionUncertainty Quantification

Methods 이 논문이 사용한 방법론

Deep Ensembles 설명 없음

Similar Papers 제목 키워드 기반

Packed-Ensemble Surrogate Models for Fluid Flow Estimation Arround Airfoil Geometries

2023-12-20 · Anthony Kalaydjian, Anton Balykov, Alexi Semiz, Adrien Chan-Hon-Tong

Physical based simulations can be very time and computationally demanding tasks. One way of accelerating these processes is by making use of data-driven surrogate models that learn from existing simulations. Ensembling m…

Enhancing Decision-Making in Windows PE Malware Classification During Dataset Shifts with Uncertainty Estimation

2025-12-20 · Rahul Yumlembam, Biju Issac, Seibu Mary Jacob arxiv

Artificial intelligence techniques have achieved strong performance in classifying Windows Portable Executable (PE) malware, but their reliability often degrades under dataset shifts, leading to misclassifications with s…

Malware Classification

Confident Neural Network Regression with Bootstrapped Deep Ensembles

2022-02-22 · Laurens Sluijterman, Eric Cator, Tom Heskes

With the rise of the popularity and usage of neural networks, trustworthy uncertainty estimation is becoming increasingly essential. One of the most prominent uncertainty estimation methods is Deep Ensembles (Lakshminara…

Prediction Intervalsregression

Uncertainty Quantification with Deep Ensembles for 6D Object Pose Estimation

2024-03-12 · Kira Wursthorn, Markus Hillemann, Markus Ulrich

The estimation of 6D object poses is a fundamental task in many computer vision applications. Particularly, in high risk scenarios such as human-robot interaction, industrial inspection, and automation, reliable pose est…

6D Pose Estimation using RGBObjectPose EstimationUncertainty Quantification

Estimating Dense-Packed Zone Height in Liquid-Liquid Separation: A Physics-Informed Neural Network Approach

2026-01-26 · Mehmet Velioglu, Song Zhai, Alexander Mitsos, Adel Mhamdi 외 arxiv

Separating liquid-liquid dispersions in gravity settlers is critical in chemical, pharmaceutical, and recycling processes. The dense-packed zone height is an important performance and safety indicator but it is often exp…