Yumin Suh

Yumin Suh

E-mail: yumin (at) nec-labs.com
CV
Google Scholar
Github


I am a senior researcher at NEC Labs America. Before joining NEC, I worked as a postdoctoral researcher at Seoul National University under the supervision of Bohyung Han and Kyoung Mu Lee. I completed my PhD at Seoul National University in 2019 under the supervision of Kyoung Mu Lee. I have a broad interest in computer vision and machine learning. Especially, my current research focuses on learning representations for multiple tasks.

Selected Publications (More)

Improving the Efficiency-Accuracy Tradeoff of DETR-Style Models in Practice

Yumin Suh, Dongwan Kim, Abhishek Aich, Samuel Schulter, Jong-Chyi Su, Bohyung Han, Manmohan Chandraker
Efficient Deep Learning for Computer Vision, CVPR Workshop 2024 [paper]

Generating Enhanced Negatives for Training Language-Based Object Detectors

Shiyu Zhao, Long Zhao, Vijay Kumar BG, Yumin Suh, Dimitris N. Metaxas, Manmohan Chandraker, Samuel Schulter
CVPR 2024 [arXiv]

Taming Self-Training for Open-Vocabulary Object Detection

Shiyu Zhao, Samuel Schulter, Long Zhao, Zhixing Zhang, Vijay Kumar BG, Yumin Suh, Manmohan Chandraker, Dimitris N. Metaxas
CVPR 2024 [arXiv]

Efficient Controllable Multi-Task Architectures

Abhishek Aich, Samuel Schulter, Amit K. Roy-Chowdhury, Manmohan Chandraker, Yumin Suh
ICCV 2023 [arXiv]

OmniLabel: A Challenging Benchmark for Language-Based Object Detection

Samuel Schulter, Vijay Kumar B G, Yumin Suh, Konstantinos M. Dafnis, Zhixing Zhang, Shiyu Zhao, Dimitris Metaxas
ICCV 2023 (Oral) [arXiv][code][project][data]

Confidence and Dispersity Speak: Characterizing Prediction Matrix for Unsupervised Accuracy Estimation

Weijian Deng, Yumin Suh, Stephen Gould, Liang Zheng
ICML 2023 [arXiv]

Controllable Dynamic Multi-Task Architectures

Dripta Raychaudhuri, Yumin Suh, Samuel Schulter, Xiang Yu, Masoud Faraki, Amit K. Roy-Chowdhury, Manmohan Chandraker
CVPR 2022 (Oral) [arXiv] [Project page]

Learning to Optimize Domain Specific Normalization for Domain Generalization

Seonguk Seo, Yumin Suh, Dongwan Kim, Geeho Kim, Jong-Woo Han, and Bohyung Han
ECCV 2020 [Paper]

Stochastic Class-based Hard Example Mining for Deep Metric Learning

Yumin Suh, Bohyung Han, Wonsik Kim, and Kyoung Mu Lee
CVPR 2019 [Paper]

Part-Aligned Bilinear Representations for Person Re-identification

Yumin Suh, Jingdong Wang, Siyu Tang, Tao Mei and Kyoung Mu Lee
ECCV 2018 [Paper] [Supp] [Code] [Poster]

Work Experience

Researcher at NEC Labs America. 2019.12 - present

Postdoctoral researcher at Seoul National University, Seoul, Korea. 2019.4 - 2019.11
Advisors: Bohyung Han, Kyoung Mu Lee

Research Intern at Microsoft Research Asia (MSRA), Beijing, China. 2016.9 - 2017.5
Advisors: Tao Mei, Jingdong Wang

Research Intern at WILLOW, Inria, Paris, France. 2014.12 - 2015.6
Advisors: Jean Ponce, Minsu Cho

Academic Services

Area Chair

ACCV 2022, CVPR 2024-2025

Senior Program Committee

IJCAI 2021, AAAI 2022

Program Committee

ACCV 2020, CVPR 2019-2023, ECCV 2020-2022, ICCV 2019-2023, ICPR 2020, MM 2017, WACV 2021
AAAI 2020-2021, ICLR 2021-2024, ICML 2020-2024, IJCAI 2022, NeurIPS 2021-2022

Journal Reviewer

TPAMI, TIP, TMM, CVIU, MMSJ, AOAS, TCSVT