Improving Accuracy and Calibration of Deep Image Classifiers With Agreement-Driven Dynamic Ensemble
One of the biggest challenges when considering the applicability of Deep Learning systems to real-world problems is the possibility of failure in <italic>critical</italic> situations. Possible strategies to tackle this problem are two-fold: (i) models need to be highly accurate, conseque...
Saved in:
Main Authors: | Pedro Conde, Rui L. Lopes, Cristiano Premebida |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2025-01-01
|
Series: | IEEE Open Journal of the Computer Society |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10806808/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Using microscopic imaging and ensemble deep learning to classify the provenance of archaeological ceramics
by: Qian Wang, et al.
Published: (2024-12-01) -
Adapting Ensemble‐Calibration Techniques to Probabilistic Solar‐Wind Forecasting
by: N. O. Edward‐Inatimi, et al.
Published: (2024-12-01) -
Effect of the Ensemble System Size on the Precipitation Forecast Accuracy
by: Atefeh Mohamadi, et al.
Published: (2022-09-01) -
HSTCN-NuSVC: A Homogeneous Stacked Deep Ensemble Learner for Classifying Human Actions Using Smartphones
by: Sarmela Raja Sekaran, et al.
Published: (2025-02-01) -
Uncertainty Quantification for Machine Learning‐Based Ionosphere and Space Weather Forecasting: Ensemble, Bayesian Neural Network, and Quantile Gradient Boosting
by: Randa Natras, et al.
Published: (2023-10-01)