Junsuk Choe
Junsuk Choe
Assistant Professor
Department of Computer Science and Engineering
Office: AS-913
Phone: +82-2-705-8495
Email / Google Scholar / CV / Calendar
Embedded Files
I am an Assistant Professor in the Department of Computer Science and Engineering at Sogang University. Before joining Sogang University in Fall 2021, I spent two wonderful years as a Research Intern and then a Research Scientist at NAVER AI Lab, where I had the good fortune to work with Dongyoon Han, Sangdoo Yun, Seong Joon Oh, Sanghyuk Chun, Byeongho Heo, and Jung-Woo Ha. I obtained my Ph.D. from the Yonsei University in 2020 under the supervision of Prof. Hyunjung Shim, and my B.S. also from the Yonsei University in 2013.
For Prospective Students: Unfortunately, we do not have any openings before the end of 2025.
News
25.02: Serving as an Area Chair for COLM 2025 and a Senior Reviewer for CoLLAS 2025.
25.01: Minyoung, Yeji, and Yejin served as visiting scholars at the Tübingen AI Center (Host: Prof. Dr. Seong Joon Oh).
24.10: Hyoseo is at Michigan State University as a visiting scholar (Host: Prof. Sijia Liu).
24.09: Granted the Global Humanities and Social Convergence Research Program (1.8B KRW) as a Co-PI from the NRF Korea (PI: Prof. Dasaem Jeong).
24.08: Dongjun received the NRF Fellowship for PhD students (20M KRW) from the NRF Korea.
24.08: Dongjun is at CMU as a visiting student, supported by the IITP AI Intensive Education Program.
24.07: Hyoseo started her research internship at NAVER AI Lab (Mentor: Dr. Dongyoon Han).
24.04: Granted the Outstanding Young Scientist Grant (900M KRW) as a PI from the NRF Korea (Co-PI: Prof. Buru Chang).
23.12: Received the Sogang College of Engineering Young Fellow Award.
23.07: Junsuk, Minyoung, and Hyoseo served as visiting scholars at the Tübingen AI Center (Host: Prof. Dr. Seong Joon Oh and Prof. Dr. Zeynep Akata).
22.10: Received the Sogang College of Engineering Outstanding Lecture Award.
21.09: Joined the Dept. of Computer Science at Sogang University as an Assistant Professor.
21.06 : Recognized as an outstanding reviewer by CVPR 2021.
20.05: Joined NAVER AI Lab as a Research Scientist.
Research Interests
Sustainable Machine Learning. Developing AI systems that maintain efficiency and adaptability over time is crucial. My research focuses on efficient continual learning, enabling models to retain knowledge while integrating new information, and machine unlearning, allowing models to remove specific knowledge without full retraining. I also explore knowledge editing techniques to refine and correct model behavior dynamically.
Minimal-Supervision AI. Reducing dependence on manually labeled data is essential for scalable AI. My work emphasizes semi-supervised and weakly-supervised learning, leveraging unlabeled and cost-effective data to improve model performance. I also study multimodal large language models, ensuring they generalize well across diverse data sources with minimal supervision.
Trustworthy and Robust AI. Ensuring AI models are reliable, transparent, and privacy-compliant is at the core of my research. I develop machine unlearning techniques to remove sensitive information while preserving model integrity and work on hallucination mitigation in multimodal large language models to enhance prediction accuracy. My research aims to build robust and interpretable AI systems that align with ethical AI principles.
Lab Members
Dongjun Hwang (PhD: 24.03-, MS: 22.03-24.02, Intern: 21.09-22.02)
Minyoung Lee (PhD: 25.03-, MS: 23.03-25.02, Intern: 22.03-23.02)
Hyoseo Kim (MS: 22.09-)
Yeji Park (Integrated MS-PhD: 23.03-, Intern: 22.10-23.02)
Yejin Kim (MS: 24.03-, Intern: 23.02-24.02)
Beomyun Kwon (MS: 25.03-, Intern: 24.12-25.02)
Jimin Hong (Intern: 25.03-)
Elena Kuular (Intern: 25.04-)
Alumni
Doyeol Baek (MS: 22.09-24.08, Intern: 22.01-22.08) → Software Engineer at Samsung Electronics
Junyong Kang (Intern: 21.12-23.03) → MS student at KAIST AI
Academic Activities
Senior Program Commitee (Area Chair & Senior Reviewer)
(Current) COLM 2025
(Past) CoLLAs 2025
Program Commitee (Reviewer)
(Current) ICCV 2025, NeurIPS 2025
(Past) CVPR, ICCV, ECCV, WACV, ACCV, ICML, ICLR, NeurIPS, AAAI, AISTATS, IEEE PAMI, IEEE TCSVT, IEEE TIP, IJCV
Organizer
Publications
J: Journal, C: Conference, W: Workshop
^Co-corresponding Authors, *Co-first Authors
Bold: Lab Members
[J12] Small Object Matters in Weakly Supervised Object Localization
Dongjun Hwang, Seong Joon Oh, Junsuk Choe.
Neurocomputing, 2025. (IF: 5.5)
[C14] NegMerge: Sign-Consensual Weight Merging for Machine Unlearning
Hyo Seo Kim, Dongyoon Han^, Junsuk Choe^.
ICML 2025.
[J11] VHOIP: Video-based Human-Object Interaction recognition with CLIP Prior knowledge
Doyeol Baek, Junsuk Choe.
Pattern Recognition Letters, 2025. (IF: 3.9)
[J10] Fog-Free Training for Foggy Scene Understanding
Minyoung Lee, Kyungwoo Song, Junsuk Choe.
Pattern Recognition Letters, 2025. (IF: 3.9)
[J9] Curriculum Learning with Class-label Composition for Weakly Supervised Semantic Segmentation
Dongjun Hwang, Hyoseo Kim, Doyeol Baek, Hyunbin Kim, Inhye Kye, Junsuk Choe.
Pattern Recognition Letters, 2025. (IF: 3.9)
[C13] ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models [code]
Yeji Park*, Deokyeong Lee*, Junsuk Choe^, Buru Chang^.
AAAI 2025.
[J8] Improving ViT Interpretability with Patch-level Mask Prediction
Junyong Kang, Byeongho Heo, Junsuk Choe.
Pattern Recognition Letters, 2025. (IF: 3.9)
[J7] Discovering an Inference Recipe for Weakly-Supervised Object Localization
Sanghuk Lee*, Cheolhyun Mun*, Youngjung Uh, Junsuk Choe, Hyeran Byun.
Patter Recognition, 2024. (IF: 7.5)
[J6] Weakly-supervised Incremental learning for Semantic segmentation with Class Hierarchy
Hyoseo Kim, Junsuk Choe.
Pattern Recognition Letters, 2024. (IF: 3.9)
[C12] Weakly Supervised Semantic Segmentation for Driving Scenes [code]
Dongseob Kim*, Seungho Lee*, Junsuk Choe, Hyunjung Shim.
AAAI 2024.
[C11] Small Objects Matters in Weakly-supervised Semantic Segmentation
Cheolhyun Mun*, Sanghuk Lee*, Youngjung Uh, Junsuk Choe, Hyeran Byun.
WACV 2024.
[C10] Neglected Free Lunch - Learning Image Classifiers Using Annotation Byproducts [code]
Dongyoon Han*, Junsuk Choe*, Seonghyeok Chun, John Chung, Minsuk Chang, Sangdoo Yun, Jean Song, Seong Joon Oh.
ICCV 2023.
[J5] Entropy Regularization for Weakly Supervised Object Localization
Dongjun Hwang, Jung-Woo Ha, Hyunjung Shim, Junsuk Choe.
Pattern Recognition Letters, 2023. (IF: 3.9)
[J4] Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets [arxiv][code]
Junsuk Choe*, Seong Joon Oh*, Sanghyuk Chun, Seungho Lee, Zeynep Akata, Hyunjung Shim.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023. (IF: 20.8)
[C9] Weakly Supervised Semantic Segmentation using Out-of-Distribution Data [code]
Jungbeom Lee, Seong Joon Oh, Sangdoo Yun, Junsuk Choe, Eunji Kim, Sungroh Yoon.
CVPR 2022.
[J3] Attention-based Dropout Layer for Weakly Supervised Single Object Localization and Semantic Segmentation [code]
Junsuk Choe*, Seungho Lee*, and Hyunjung Shim.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021. (IF: 24.314)
[C8] Keep CALM and Improve Visual Feature Attribution [code]
Jae Myung Kim*, Junsuk Choe*, Zeynep Akata, Seong Joon Oh.
ICCV 2021.
[C7] Normalization Matters in Weakly Supervised Object Localization [code]
Jeesoo Kim, Junsuk Choe, Sangdoo Yun, Nojun Kwak.
ICCV 2021.
[C6] Contrastive Attention Maps for Self-supervised Co-localization
Minsong Ki, Youngjung Uh, Junsuk Choe, Hyeran Byun.
ICCV 2021.
[C5] Rethinking Spatial Dimensions of Vision Transformers [code]
Byeongho Heo, Sangdoo Yun, Dongyoon Han, Sanghyuk Chun, Junsuk Choe, Seong Joon Oh.
ICCV 2021.
[J2] Region-based Dropout with Attention Prior for Weakly Supervised Object Localization
Junsuk Choe, Dongyoon Han, Sangdoo Yun, Jung-Woo Ha, Seong Joon Oh, Hyunjung Shim.
Pattern Recognition, 2021. (Q1; IF: 8.518)
[C4] Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels [code]
Sangdoo Yun, Seong Joon Oh, Byeongho Heo, Dongyoon Han, Junsuk Choe, Sanghyuk Chun.
CVPR 2021.
[C3] Evaluating Weakly Supervised Object Localization Methods Right [code]
Junsuk Choe*, Seong Joon Oh*, Seungho Lee, Sanghyuk Chun, Zeynep Akata, Hyunjung Shim.
CVPR 2020.
[C2] CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features [code]
Sangdoo Yun, Dongyoon Han, Seong Joon Oh, Sanghyuk Chun, Junsuk Choe, Youngjoon Yoo.
ICCV 2019. (Oral presentation)
[C1] Attention-based Dropout Layer for Weakly Supervised Object Localization [code]
Junsuk Choe, Hyunjung Shim.
CVPR 2019. (Oral presentation)
[W2] An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods
Sanghyuk Chun, Seong Joon Oh, Sangdoo Yun, Dongyoon Han, Junsuk Choe, Youngjoon Yoo.
ICML 2019 Workshop on Uncertainty & Robustness in Deep Learning.
[J1] Robust approach to inverse lighting using RGB-D images
Junsuk Choe, Hyunjung Shim.
Information Sciences, 2018. (IF: 5.524)
[W1] Face generation for low-shot learning using generative adversarial networks
Junsuk Choe*, Song Park*, Kyungmin Kim*, Joo Hyun Park*, Dongseob Kim*, Hyunjung Shim.
ICCV 2017 Workshop on MS-Celeb-1M Challenge. (Oral presentation)
Page updated
Google Sites
Report abuse