Skip to main navigation
Skip to search
Skip to main content
Hong Kong Baptist University Home
Help & FAQ
Home
Scholars
Departments / Units
Research Output
Projects / Grants
Prizes / Awards
Activities
Press/Media
Student theses
Datasets
Search by expertise, name or affiliation
Energy-Based Open-World Uncertainty Modeling for Confidence Calibration
Yezhen Wang
*
, Bo Li
, Tong Che
,
Kaiyang Zhou
, Ziwei Liu
, Dongsheng Li
*
Corresponding author for this work
Department of Computer Science
Research output
:
Chapter in book/report/conference proceeding
›
Conference proceeding
›
peer-review
60
Citations (Scopus)
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Energy-Based Open-World Uncertainty Modeling for Confidence Calibration'. Together they form a unique fingerprint.
Sort by:
Weight
Alphabetically
Keyphrases
Softmax
100%
Model Uncertainty
100%
Energy-based
100%
Global Uncertainty
100%
Open World
100%
Confidence Calibration
100%
State-of-the-art Techniques
33%
Classification Accuracy
33%
Discriminative Classifier
33%
Data Distribution
33%
High Probability
33%
Existing State
33%
Deep Neural Network
33%
Classification Task
33%
K(I)
33%
Machine Learning System
33%
Cross-entropy Loss
33%
Overconfident Prediction
33%
Decision Reliability
33%
Closed World
33%
Computer Science
Model Uncertainty
100%
Classification Accuracy
50%
Data Distribution
50%
Objective Function
50%
Deep Neural Network
50%
Classification Task
50%
Machine Learning
50%
Correctness
50%