Zhongyi Han
12 papers · 2020–2026 · 5 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 ↓+3 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (30) π Academic Marathon Β· Sprint π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π€ Dynamic Duo (11)
π
Trend Setter
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(65)
Venues
Top co-authors
Research topics
Machine Learning
(10)
Learning Types Β· Machine Learning
(8)
Deep Learning
(7)
Artificial Intelligence
(5)
Application Areas
(5)
Learning Types Β· Deep Learning
(5)
Core AI
(4)
Core Methods
(4)
Learning Paradigms
(2)
Optimization & Theory Β· Machine Learning
(2)
Optimization & Theory Β· Deep Learning
(2)
Architectures
(1)
Bayesian & Probabilistic
(1)
Keywords
transfer learning
(3)
source-free domain adaptation
(3)
label noise
(2)
out-of-distribution detection
(2)
energy score
(2)
domain adaptation
(2)
distribution shift
(2)
neural network
(2)
semi-supervised learning
(2)
knowledge transfer
(1)
noisy label learning
(1)
curriculum learning
(1)
feature learning
(1)
in-context learning
(1)
image classification
(1)
feature selection
(1)
discriminative learning
(1)
bayesian inference
(1)
class imbalance
(1)
computer vision
(1)
Papers
Retriever Encoder Selection Matters for In-Context Learning-based Medical Segmentation
AAAI 2026
Stabilizing Feature Geometry in Noisy Pretrained Models for Robust Downstream Tasks
CVPR 2026
Discriminability-Driven Channel Selection for Out-of-Distribution Detection
CVPR 2024
Exploring Channel-Aware Typical Features for Out-of-Distribution Detection
AAAI 2024
Discriminability and Transferability Estimation: A Bayesian Source Importance Estimation Approach for Multi-Source-Free Domain Adaptation
AAAI 2023
MHPL: Minimum Happy Points Learning for Active Source Free Domain Adaptation
CVPR 2023
Subclass-Dominant Label Noise: A Counterexample for the Success of Early Stopping
NeurIPS 2023
Exploring Domain-Invariant Parameters for Source Free Domain Adaptation
CVPR 2022
Not All Parameters Should Be Treated Equally: Deep Safe Semi-supervised Learning under Class Distribution Mismatch
AAAI 2022
Safe-Student for Safe Deep Semi-Supervised Learning With Unseen-Class Unlabeled Data
CVPR 2022
SNAIL: Semi-Separated Uncertainty Adversarial
Learning for Universal Domain Adaptation
ACML 2022
Towards Accurate and Robust Domain Adaptation under Noisy Environments
IJCAI 2020