Packed-Ensembles for Efficient Uncertainty Estimation
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.
Code (1)
Tasks
Classifier calibrationDiversityImage ClassificationOut-of-Distribution DetectionUncertainty QuantificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Packed-Ensemble Surrogate Models for Fluid Flow Estimation Arround Airfoil Geometries
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
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 ClassificationConfident Neural Network Regression with Bootstrapped Deep Ensembles
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 IntervalsregressionUncertainty Quantification with Deep Ensembles for 6D Object Pose Estimation
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 QuantificationEstimating Dense-Packed Zone Height in Liquid-Liquid Separation: A Physics-Informed Neural Network Approach
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…