Changkun Ye
4 papers · 2023–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🗺️
Taxonomy Completionist
(11)
Top co-authors
Research topics
Machine Learning
(4)
Core Methods
(4)
Optimization & Theory · Machine Learning
(4)
Artificial Intelligence
(2)
Application Areas
(2)
Deep Learning
(1)
Core AI
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Learning Types · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
model calibration
(2)
label shift
(2)
bayesian inference
(1)
em algorithm
(1)
confidence calibration
(1)
posterior sampling
(1)
label smoothing
(1)
class imbalance
(1)
markov chain monte carlo
(1)
maximum a posteriori
(1)
monte carlo sampling
(1)
distribution shift
(1)
maximum likelihood estimation
(1)
deep neural network
(1)
out-of-distribution detection
(1)
cross entropy
(1)
confidence estimation
(1)
label distribution
(1)
vicinal risk minimization
(1)
binary classification
(1)
Papers
Open Set Label Shift with Test Time Out-of-Distribution Reference
CVPR 2025
Label Shift Estimation for Class-Imbalance Problem: A Bayesian Approach
WACV 2024
Self-Calibrating Vicinal Risk Minimisation for Model Calibration
CVPR 2024
Model Calibration in Dense Classification with Adaptive Label Perturbation
ICCV 2023