Close

Beomyoung Kim

AI Research Engineer

Download Resume

About Me


Circular Image

I am an AI research engineer at NAVER and a Ph.D. student at the Graduate School of AI at KAIST, under the guidance of Professor Sung Ju Hwang in MLAI Lab. My primary research interests lie in advancing the field of comprehensive image recognition techniques in real-world scenarios, particularly focusing on image segmentation and object detection.


In my research journey, I am deeply involved in exploring cutting-edge technologies such as vision foundation models like SAM, as well as developing multi-modal vision models. Additionally, I am actively engaged in pioneering label-efficient segmentation methods, including weakly or semi-supervised image segmentation. Another area of my focus is continual learning in image segmentation, where I strive to push the boundaries of knowledge and innovation.


Through my work, I aspire to contribute significantly to the advancement of artificial intelligence and its applications in solving real-world challenges. I am driven by a passion for innovation and a relentless pursuit of excellence in research and development.


News

Experience

NAVER

CLOVA VISION - Image Vision

AI Research Engineer at Naver Clova Vision Image-Vision team.

NAVER

CLOVA VISUAL AI - FACE

Internship at Naver Clova Visual AI FACE team.

Hyundai Mobis

Autonomous Driving Advanced Development Team (์ž์œจ์ฃผํ–‰์„ ํ–‰๊ฐœ๋ฐœํŒ€)

Internship at Hyundai Mobis Autonomous Driving Advanced Development Team.

NAVER

CLOVA VISION - OCR

Internship at Naver Clova Vision OCR team.

Military Service

Education

Korea Advanced Institute of Science and Technology (KAIST)

September 2022 - Current

Ph.D student, Kim Jaechul Graduate School of AI

Machine Learning and Artificial Intelligence (MLAI) Lab under the supervision of Prof. Sung Ju Hwang.

Korea Advanced Institute of Science and Technology (KAIST)

March 2019 - February 2021

Master Degree, Electrical Engineering, Division of Future Vehicle

Statistical Inference & Information Theory (siit) Lab under the supervision of Prof. Junmo Kim.

Inha University

March 2013 - February 2019

Bachelor Degree, Information and Communication Engineering

Inha University, Information and Communication Engineering, Bachelor Degree.

Publication

ZIM: Zero-Shot Image Matting for Anything

Beomyoung Kim, Chanyong Shin, Joonhyun Jeong, Hyungsik Jung, Se-Yun Lee, Sewhan Chun, Dong-Hyun Hwang, Joonsang Yu

Arxiv Preprint [project page] [paper] [code]

Towards Label-Efficient Human Matting: A Simple Baseline for Weakly Semi-Supervised Trimap-Free Human Matting

Beomyoung Kim, Myeong Yeon Yi, Joonsang Yu, Young Joon Yoo, Sung Ju Hwang

Arxiv Preprint [paper] [code]

Rethinking Saliency-Guided Weakly-Supervised Semantic Segmentation

Beomyoung Kim, Donghyeon Kim, Sung Ju Hwang

Arxiv Preprint [paper] [code]

ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning

Beomyoung Kim, Joonsang Yu, Sung Ju Hwang

CVPR 2024 [paper] [code]

EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection

Joonhyun Jeong, Beomyoung Kim, Joonsang Yu, Youngjoon Yoo

WACV 2024 [paper] [code]

The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation

Beomyoung Kim, Joonhyun Jeong, Dongyoon Han, Sung Ju Hwang

CVPR 2023 [paper] [code]

Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement

Beomyoung Kim, Youngjoon Yoo, Chaeeun Rhee, Junmo Kim

CVPR 2022 [paper] [code]

Learning Features with Parameter-Free Layers

Dongyoon Han, Youngjoon Yoo, Beomyoung Kim, Byeongho Heo

ICLR 2022 [paper] [code]

TricubeNet: 2D Kernel-Based Object Representation for Weakly-Occluded Oriented Object Detection

Beomyoung Kim, Janghyeon Lee, Sihaeng Lee, Doyeon Kim, and Junmo Kim

WACV 2022 [paper] [code]

SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning

Sungmin Cha*, Beomyoung Kim*, Youngjoon Yoo, and Taesup Moon (* equal contribution)

NeurIPS 2021 [paper] [code]

Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation

Beomyoung Kim, Sangeun Han, and Junmo Kim

AAAI 2021 [paper] [code]

3D Point Cloud Upsampling and Colorization using GAN

Beomyoung Kim, Sangeun Han, Eojindl Yi, and Junmo Kim

MIWAI 2021 [paper]

Fully automated valet parking system based on infrastructure sensing

Hyunjee Ryu, Beomyoung Kim, Heecheol Yoo, and Jungwon Lee

RiTA 2020 [paper]

Academic Activity

Conference Reviewer

  • CVPR 2024, ICLR 2024, AAAI 2024, ECCV 2024

  • CVPR 2023, ICCV 2023, NeurIPS 2023, WACV 2023

Skills

Get in Touch