Out-of-Distribution (OOD) data detection
Continual Learning
2022. 03. - present: Ph.D. student in the School of Integrated Technology, GIST
2020. 03. - 2022.02: M.S. student in the School of Integrated Technology, GIST
2015. 03. - 2020. 02.: B.S. in the department of computer engineering, Hanbat National University
Yu, Y.; Kim, Y.-J. Attention-LSTM-Attention Model for Speech Emotion Recognition and Analysis of IEMOCAP Database. Electronics 2020, 9, 713
Y. Yu and Y. J. Kim, ‘‘Two-dimensional attention-based LSTM model for stock index prediction,’’ J. Inf. Process. Syst., vol. 15, no. 5, pp. 1231–1242, Oct. 2019.
Seunghyeok Back, Seongju Lee, Sungho Shin, Yeonguk Yu, Taekyeong Yuk, Saepomi Jong, Seungjun Ryu, Kyoobin Lee, "Robust skin disease classification by distilling deep neural network ensemble for the mobile diagnosis of Herpes zoster", IEEE ACCESS, (2021)
Sungho Shin, Jongwon Kim, Yeonguk Yu, Seongju Lee, Kyoobin Lee, "Self-Supervised Transfer Learning from Natural Images for Sound Classification", APPLIED SCIENCES, (2021)
Seongju Lee*, Yeonguk Yu, Seunghyeok Back, Hogeon Seo, Kyoobin Lee, "SleePyCo: Automatic Sleep Scoring with Feature Pyramid and Contrastive Learning", Expert Systems with Applications, (2024)
Yeonguk Yu, Sungho Shin, Minhwan Ko, Kyoobin Lee, "Exploring using jigsaw puzzles for out-ofdistribution detection", COMPUTER VISION AND IMAGE UNDERSTANDING, (2024)
Yu, Y.; Kim, Y. A Voice Activity Detection Model Composed of Bidirectional LSTM and Attention Mechanism. In Proceedings of the 2018 IEEE 10th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM), Baguio City, Philippines, 29 November–2 December 2018; pp. 1–5
Sungho Shin, Joosoon Lee, Junseok Lee, Yeonguk Yu, Kyoobin Lee, Teaching Where to Look: Attention Similarity Knowledge Distillation for Low Resolution Face Recognition, European Conference on Computer Vision (ECCV), 2022
Yeonguk Yu, Sungho Shin, Seongju Lee, Changhyun Jun, and Kyoobin Lee, "Block Selection Method for Using Feature Norm in Out-of-distribution Detection", IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), Vancouver, Canada (Jun. 2023)
Yeonguk Yu, Sungho Shin, Seunghyeok Back, Minhwan Ko, Sangjun Noh, Kyoobin Lee, "DomainSpecific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptation", IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), Seattle, United States (Jun. 2024)
Seongju Lee, Junseok Lee, Yeonguk Yu, Taeri Kim, and Kyoobin Lee "MART: MultiscAle Relational Transformer Networks for Multi-agent Trajectory Prediction", European Conference on Computer Vision (ECCV 2024), Milan, Italy (Oct. 2024)
Yeonguk Yu, Minhwan Ko, Sungho Shin, Kangmin Kim, and Kyoobin Lee, "Curriculum Fine-tuning of Vision Foundation Model for Medical Image Classification Under Label Noise", The Conference on Neural Information Processing Systems (NeurIPS 2024), Vancouver, Canada (Dec. 2024)
OOD 객체 탐지 방법 및 시스템 [등록] / 대한민국 / 10-2567558
합성곱 신경망의 특징 맵에 기반한 분포 외 탐지 시스템 및 방법 [출원] / 대한민국 / 10-2023-0007306
OUT-OF-DISTRIBUTION DETECTION SYSTEM AND METHOD BASED ON FEATURE MAP OF CONVOLUTIONAL NEURAL NETWORK [출원] / 미국 / 18/518,159
직소 이미지 기반의 딥러닝 모델 학습 방법 및 시스템, 이를 이용한 분포 외 객체 탐지 방법 및 시스템 [출원] / 대한민국/ 10-2024-0083274
블록 선택 및 교사 모델에 기반한 딥러닝 모델 실시간 적응 방법 및 시스템 [출원] / 대한민국 / 10-2024-0083249
GIST Presidential Fellowship, Gwangju Institude of Science and Technology (GIST), Korea (Mar. 2022)
제 1회 NIA-GIST AI-HUB 인공지능 경진대회, National Information Society Agency (NIA), Korea (Sep. 2022), 2등 수상
KAIST ExploreCSR: Rising Stars 2024 / Selected as AI/CS/EE Rising Stars 2024 supported by Google exploreCSR / Invited talk about continual learning of deep neural networks [Page]
2020 - 2023: 다수 로봇의 지능을 통합 고도화하는 클라우드 로봇 지능 증강, 공유 및 프레임워크 기술 개발 (과학기술정보통신부)
2022 - present : 스스로 불확실성을 자각하며 질문하면서 성장하는 에이전트 기술 개발 (과학기술정보통신부)
2024 - present : Development of Edge AI SW technology for autonomous robotics to improve the success rate of complex tasks in daily life spaces (과학기술정보통신부)
2023-2024 : Development of test-time domain adaptation method for mobile robot in adverse weather conditions (LG 전자)