Sungha Choi
13 papers · 2019–2026 · 4 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 ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Bronze π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (27)
π§¬
Topic Evolution
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
ποΈ
Keyword Collector
(56)
Top co-authors
Research topics
Machine Learning
(8)
Application Areas
(7)
Computer Vision
(6)
Deep Learning
(6)
Learning Types Β· Machine Learning
(5)
Analysis
(4)
Learning Types Β· Deep Learning
(4)
Techniques
(4)
Artificial Intelligence
(3)
Core AI
(2)
Domain-Specific
(2)
Generation
(2)
Models
(2)
Core Methods
(1)
Learning Paradigms
(1)
Keywords
semantic segmentation
(5)
domain generalization
(3)
test-time adaptation
(3)
urban scene
(2)
domain adaptation
(2)
unsupervised domain adaptation
(1)
feature learning
(1)
catastrophic forgetting
(1)
style transfer
(1)
entropy minimization
(1)
attention mechanism
(1)
knowledge distillation
(1)
semi-supervised learning
(1)
image-to-image translation
(1)
text-to-image generation
(1)
image translation
(1)
anomaly detection
(1)
deep learning
(1)
higher-order statistics
(1)
continual learning
(1)
Papers
Concept-Aware LoRA for Domain-Aligned Segmentation Dataset Generation
CVPR 2026
CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation
CVPR 2025
Understanding Personal Concept in Open-Vocabulary Semantic Segmentation
ICCV 2025
Feature Diversification and Adaptation for Federated Domain Generalization
ECCV 2024
EcoTTA: Memory-Efficient Continual Test-Time Adaptation via Self-Distilled Regularization
CVPR 2023
Progressive Random Convolutions for Single Domain Generalization
CVPR 2023
Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization
ICCV 2023
TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation
ICLR 2023
Improving Test-Time Adaptation via Shift-Agnostic Weight Regularization and Nearest Source Prototypes
ECCV 2022
RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening
CVPR 2021
Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation
ICCV 2021
Cars Can't Fly Up in the Sky: Improving Urban-Scene Segmentation via Height-Driven Attention Networks
CVPR 2020
Image-To-Image Translation via Group-Wise Deep Whitening-And-Coloring Transformation
CVPR 2019