Kwanyoung Kim

Ph.D Candidate

Bio Imaging, Signal Processing & Learning Lab (BISPL) [Link] .

Korea Advanced Institute of Science and Technology [KAIST]

cubeyoung [at] kaist.ac.kr

Download my [CV]

Research Interests

Inverse Image problems
Large Multi-modal Model
Distribution Matching for Alignment
Active Learning

Education

Ph. D., Kim Jae Chul Graduate School of AI (Sep. 2020 - Aug. 2024)
- Korea Advanced Institute of Science and Technology (KAIST), South Korea
- Fields : Deep Learning, Biomedical Imaging
  - - Thesis Title : "Score Matching Based Self-Supervised Image Denoising and Parameter Estimation"
- Advisor: Prof. Jong Chul Ye
M. S., Electrical Engineering (Aug. 2018 - Aug. 2020)
- Ulsan National Institute of Science and Technology (UNIST), South Korea
- Fields : Computer Vision, Biomedical Imaging
- Thesis Title : "Unsupervised Training of Denoisers for Low-Dose CT Reconstruction Without Full-Dose Ground Truth"
- Advisor: Prof. Se Young Chun, (He is currently in Seoul National University, SNU )
B. S., Electrical and Computer Engineering (Feb. 2012 - Aug. 2018)
- - - Ulsan National Institute of Science and Technology (UNIST), South Korea, Summa Cum laude

News

2024

I ended my Ph.D course at August, 2024
Our Paper accepted to ICLR 2024
Our Paper accepted to ICASSP 2024, IPIU 2024

2023

I won the best poster award KOSAIM 2023

Selected Publications

LMM-Assisted Breast Cancer Treatment Target Segmentation with Consistency Embedding

Kwanyoung Kim*, Yujin Oh*, Sangjoon Park*, Hwa Kyung Byun, Jin Sung Kim, Yong Bae Kim, Jong Chul Ye, *equal contribution

[paper], under IEEE TMI Special Issue Review

OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation

Kwanyoung Kim*, Yujin Oh*, Jong Chul Ye, *equal contribution

[paper] [code] , under ECCV2024 Review

UNICORN: Ultrasound Nakagami Imaging via Score Matching and Adaptation

Kwanyoung Kim*, Jaa-Yeon Lee*, Jong Chul Ye,

*equal contribution

[paper] , under MICAAI2024 Review

Noise2One: One-Shot Image Denoising wtih Local Implicit Learning

Kwanyoung Kim, Jong Chul Ye,

ICASSP2024, IPIU2024 (First author)

[paper]

Unpaired Image-to-Image Translation via Neural Schrödinger Bridge

BeumSu Kim*, Gihyun Kwon*, Kwanyoung Kim, Jong Chul Ye, *equal contribution

ICLR2024

[paper]

ZegOT: Zero-shot Segmentation Through Optimal Transport of Text Prompts

Kwanyoung Kim*, Yujin Oh*, Jong Chul Ye, *equal contribution

[paper] [Preprint]

Noise Distribution Adaptive Self-Supervised Image Denoising using Tweedie Distribution and Score Matching

Kwanyoung Kim, Taesung Kwon, Jong-Chul Ye

CVPR 2022 (First author)

Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Images

Kwanyoung Kim, Jong Chul Ye

NeurIPS 2021 (First author)

Task-Aware Variational Adversarial Active Learning

Kwanyoung Kim, Dongwon Park, Kwang In Kim, Se Young Chun

CVPR 2021 (First author)

Awards

3rd Award in NTIRE 2018 Image Super Resolution Challenge Track 2&3 – x4 Denoising & Super resolution (CVPR Workshop), [Award Certificate]
Honorable Mention Award in NTIRE 2018 Image Super Resolution Challenge Track 1 – x8 Super resolution (CVPR Workshop), [Award Certificate]

Academic Service

Reviewer

Journals:

IEEE Signal processing magazine (2021-)
Medical Image Analysis (2021-)
IEEE Transactions on Pattern Analysis and Machine Intelligence (2022-)