Scholar
Jaehyun Choi
Google Scholar ID: n-OTCygAAAAJ
PhD Candidate @ KAIST
Citations & Impact
Citations
149
H-index
7
i10-index
5
Publications
18
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- [{'Paper': 'PSGM-TR: A Transformer-Based Approach for Pulmonary Segment Segmentation Using Gaussian Mixture Models', 'Conference': 'Workshop on Shape in Medical Imaging @ MICCAI 2025'}, {'Paper': 'AH-OCDA: Amplitude-based Curriculum Learning and Hopfield Segmentation Model for Open Compound Domain Adaptation', 'Conference': 'WACV 2025'}, {'Paper': 'Self-supervised Transformation Learning for Equivariant Representations', 'Conference': 'NeurIPS 2024'}, {'Paper': 'Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance', 'Conference': 'NeurIPS 2024 (Bronze Prize - Samsung HumanTech Paper Awards)'}, {'Paper': 'PSGMM: Pulmonary Segment Segmentation Based on Gaussian Mixture Model', 'Conference': 'Workshop on Shape in Medical Imaging @ MICCAI 2024'}, {'Paper': 'Learning Neural Deformation Representation for 4D Dynamic Shape Generation', 'Conference': 'ECCV 2024'}, {'Paper': 'Stereo-Matching Knowledge Distilled Monocular Depth Estimation Filtered by Multiple Disparity Consistency', 'Conference': 'ICASSP 2024'}, {'Paper': 'Modeling Stereo-Confidence Out of the End-to-End Stereo-Matching Network via Disparity Plane Sweep', 'Conference': 'AAAI 2024'}, {'Paper': 'Expanding Expressiveness of Diffusion Models with Limited Data via Self-Distillation based Fine-Tuning', 'Conference': 'WACV 2024'}, {'Paper': 'Few-Shot Anomaly Detection with Adversarial Loss for Robust Feature Representation', 'Conference': 'BMVC 2023'}, {'Paper': 'TCX: Texture and Channel Swappings for Domain Generalization', 'Journal': 'Pattern Recognition Letters (Impact Factor: 5.1)'}, {'Paper': 'Data Poisoning Attack Aiming the Vulnerability of Continual Learning', 'Conference': "ICIP 2023 (ML Safety@NeurIPS'22)"}, {'Paper': 'Deep Cross-Modal Steganography using Neural Representations', 'Conference': 'ICIP 2023 (Oral)'}, {'Paper': 'Multi-Scale Foreground-Background Separation for Light Field Depth Estimation with Deep Convolutional Networks', 'Journal': 'Pattern Recognition Letters (Impact Factor: 5.1)'}, {'Paper': 'Reinforcement Learning-Based Black-Box Model Inversion Attacks', 'Conference': 'CVPR 2023'}]
Background
- Research interests include distribution matching (dataset condensation and domain adaptation/generalization), AI safety (explainable deepfake detection), and generative models. During his master's, he was a member of the VC Lab at SKKU.
Co-authors