Biography

I’m a PhD candidate of Data Science and Artificial Intelligence Laboratory (DSAIL) in the Electrical & Computer Engineering department at the Seoul National University, South Korea. I received B.S. degree in Electrical Engineering from Seoul National University, South Korea, in 2017. My research interests involve deep learning applied to computer vision problem, especially label-efficient learning such as weakly and semi-supervised learning.

Education

  • PhD. Electrical and Computer Engineering, Seoul National University (2017.3-2023.2, expected)
  • BS. Electrical and Computer Engineering, Seoul National University (2013.3-2017.2)

Research Experiences

  • Research Internship in Amazon, Seattle, USA (Jun. 2022 - Sep. 2022)
  • Research Internship in Naver AI Lab, Seongnam, South Korea (Sep. 2021 - Nov. 2021, Apr. 2022 - May 2022)

Publications

2022

Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization
Jungbeom Lee, Eunji Kim, Jisoo Mok, and Sungroh Yoon
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022. in press.
[Paper] [code]

Weakly Supervised Semantic Segmentation using Out-of-Distribution Data
Jungbeom Lee, Seong Joon Oh, Sangdoo Yun, Junsuk Choe, Eunji Kim, and Sungroh Yoon
Computer Vision and Pattern Recognition (CVPR), 2022.
[Paper] [code]

Perception Prioritized Training of Diffusion Models
Jooyoung Choi, Jungbeom Lee, Chaehun Shin, Sungwon Kim, Hyunwoo Kim, and Sungroh Yoon
Computer Vision and Pattern Recognition (CVPR), 2022.
[Paper] [code]

Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization
Eunji Kim, Siwon Kim, Jungbeom Lee, Hyunwoo Kim, and Sungroh Yoon
Computer Vision and Pattern Recognition (CVPR), 2022.
[Paper]

2021

Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation
Jungbeom Lee, Jooyoung Choi, Jisoo Mok, and Sungroh Yoon
Neural Information Processing Systems (NeurIPS), 2021
[Paper] [code]

Toward Spatially Unbiased Generative Models
Jooyoung Choi, Jungbeom Lee, Yonghyun Jeong, and Sungroh Yoon
International Conference on Computer Vision (ICCV), 2021
[Paper] [code]

Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation
Jungbeom Lee, Eunji Kim, and Sungroh Yoon
Computer Vision and Pattern Recognition (CVPR), 2021.
[Paper] [code]

BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation
Jungbeom Lee, Jihun Yi, Chaehun Shin, and Sungroh Yoon
Computer Vision and Pattern Recognition (CVPR), 2021.
[Paper] [code]

2019

Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentation
Jungbeom Lee, Eunji Kim, Sungmin Lee, Jangho Lee, and Sungroh Yoon
International Conference on Computer Vision (ICCV), 2019
[Paper]

Mutual Suppression Network for Video Prediction using Disentangled Features
Jungbeom Lee, Jangho Lee, Sungmin Lee, and Sungroh Yoon
British Machine Vision Conference (BMVC), 2019
[Paper]

FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference
Jungbeom Lee, Eunji Kim, Sungmin Lee, Jangho Lee, and Sungroh Yoon
Computer Vision and Pattern Recognition (CVPR), 2019.
[Paper]