ECUQ(Environment Conditioned Uncertainty Quantification) method

Read full text
Authors: jie liu
Cited by: 0

Abstract

Source code release (v2.0) accompanying the revised manuscript: Jie Liu, Weijian Qiu, Zhuohong Wu. "Physics-Guided Environment-Conditioned Uncertainty Quantification for Trustworthy Object Detection under Visual Degradation." Submitted to The Visual Computer, 2026. If you use this code, the data, or any part of this release, please cite the accompanying manuscript. A machine-readable citation is provided in the companion CITATION.cff file on this record. v2.0 updates the documentation to align with the revised manuscript (new title, paper-figure/table-to-script mapping, machine-readable citation file). Source code, checkpoints, and JSON evaluation results are byte-identical to v1.0; all numerical results in the revised manuscript are fully reproducible by rerunning the included scripts on the listed datasets. See CHANGELOG.md for full release notes. Files in this record: - code_ecuq.zip : full source code archive - README.txt : usage documentation - CITATION.cff : machine-readable citation - CHANGELOG.md : v2.0 release notes

Fields of Study & Subjects

Advanced Neural Network Applications Adversarial Robustness in Machine Learning Video Surveillance and Tracking Methods

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
1 March 2026
Language
EN
Document type
Dataset