Prof. Youngwook Kim - Kookmin University AI·SW Graduate School

Research Overview 연구 개요

The AI Vision Lab conducts computer vision research centered on Applied Vision (leveraging image data across diverse domains) and Intelligent Vision (enabling robust learning despite incomplete information). Research areas include geospatial AI, autonomous driving AI, medical AI, multimodal AI, and data-robust AI.

AI Vision Lab은 다양한 도메인에서 이미지 데이터를 활용하는 Applied Vision과 불완전한 정보 속에서도 강건한 학습을 가능하게 하는 Intelligent Vision을 중심으로 컴퓨터 비전 연구를 수행합니다. 주요 연구 분야로는 지리공간 AI, 자율주행 AI, 의료 AI, 멀티모달 AI, 데이터 강건 AI가 있습니다.

Research Areas 연구 분야

Geospatial AI
Autonomous Driving AI
Medical AI
Multimodal AI
Data-robust AI

지리공간 AI
자율주행 AI
의료 AI
멀티모달 AI
데이터 강건 AI

Major Achievements 주요 연구 성과

2025 Satellite Image Utilization Research Program selection
2025 AI Star Fellowship Program selection

Recent Publications 주요 논문

Y. Kim, "Leveraging Single Positive Class Label Supervision for Weakly Supervised Semantic Segmentation," IEEE Access, 2025
M. Jung, S. Jeong, Y. Kim, and J. Lee, "EDAS: Effective Data Augmentation Strategies for test-time adaptation," ICT Express, 2025
J. Shin, Y. Kim, and J. Lee, "A Plug-In Curriculum Scheduler for Improved Deformable Medical Image Registration," IEEE Access, 2025
J. Shin, Y. Kim, S. Hong, and J. Lee, "Learning Dual Hierarchical Representation for 3D Surface Reconstruction," ACCV, 2024
Y. Kim, S. Kim, Y. Ro, and J. Lee, "Instance-Dependent Multilabel Noise Generation for Multilabel Remote Sensing Image Classification," IEEE JSTARS, 2024
Y. Kim, J. M. Kim, J. Jeong, C. Schmid, Z. Akata, and J. Lee, "Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification," CVPR, 2023
Y. Kim, J. M. Kim, Z. Akata, and J. Lee, "Large Loss Matters in Weakly Supervised Multi-Label Classification," CVPR, 2022