I am a 5th year Ph.D. student advised by Prof. Kuk-Jin Yoon at Visual Intelligence Lab (VILab), Korea Advanced Institute of Science and Technology (KAIST). I am set to graduate in February 2025 and am actively seeking a postdoctoral or research position.

I am dedicated to advancing the understanding and prediction of environmental data through innovative approaches that utilize minimal or weak annotations, significantly reducing the annotation burden. I have tackled a range of tasks such as semantic segmentation, data completion, and representation learning, consistently pushing the boundaries of these fields. My expertise spans various data modalities, including image, point cloud, and event data.

My CV can be found here.

Publications

TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight
H. Jang*, J. Kim*, H. Kweon*, K. Yoon
NeurIPS 2024
[paper]

Finding Meaning in Points: WSSS for Event Cameras
H. Cho*, S. Yoon*, H. Kweon*, K. Yoon
ECCV 2024
[paper]

From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation
H. Kweon, K. Yoon
CVPR 2024 Oral (3.3% of accepted)
[paper]

Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle
H. Kweon*, J. Kim*, K. Yoon
CVPR 2024
[paper]

Learning Point Cloud Completion without Complete Point Clouds: A Pose-aware Approach
J. Kim, H. Kweon, Y. Yang, K. Yoon
ICCV 2023
[paper]

Weakly Supervised Semantic Segmentation via Adversarial Learning of Classifier and Reconstructor
H. Kweon*, S. Yoon*, K. Yoon
CVPR 2023
[paper]

Pixel-wise Warping for Deep Image Stitching
H. Kweon*, H. Kim*, Y. Kang*, Y. Yoon*, W. Jeong, Yoon, K. Yoon
AAAI 2023
[paper]

Joint Learning of 2D-3D Weakly Supervised Semantic Segmentation
H. Kweon, K. Yoon
NeurIPS 2022
[paper]

Adversarial Erasing Framework via Triplet with Gated Pyramid Pooling Layer for Weakly Supervised Semantic Segmentation
S. Yoon*, H. Kweon*, J. Cho, S. Kim, K. Yoon
ECCV 2022
[paper]

Unlocking the Potential of Ordinary Classifier: Class-specific Adversarial Erasing Framework for Weakly Supervised Semantic Segmentation
H. Kweon*, S. Yoon*, H. Kim, D. Park, K. Yoon
ICCV 2021
[paper]

Selected Honors and Awards

• Reviewer of Top-tier Conferences / CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, AAAI
  
• Reviewer of Top-tier Journals / TPAMI, IJCV, CVIU
  
• 2023 / Bronze prize in Samsung HumanTech Paper Awards 2023
  
• 2023 / Bronze prize in Best Paper Awards during IPIU 2023, 35th Workshop on Image Processing and Image Understanding
  
• 2022 / Gold prize in Best Paper Awards during IPIU 2022, 34th Workshop on Image Processing and Image Understanding
  
• 2021 / Winning CVPRW 2021 DSEC challenge (event-only track)
  

Projects

• 2020 ~ present / Unmanned Swarm CPS Research Laboratory Program of Defense Acquisition Program / drone imaging, image stitching, 3D reconstruction, and point cloud semantic segmentation
  
• 2021 ~ 2023 / AI Research for Intelligent X-ray Luggage Scanning System / X-ray imaging, object detection, weakly supervised object localization
  
• 2021 ~ 2022 / Development of Situational Awareness System to Prevent Collisions and Accidents for Autonomous Ships / semantic segmentation, small object detection