Yechan Kim
Portrait of Yechan Kim

I study how machines
learn to see and act

AffiliationLIG Defense&Aerospace, AI Laboratory

LocationPangyo House, Republic of Korea

Research

Projects
01

Representation Learning

Learn robust and transferable representations that generalize across changing environments, sensing conditions, and data distributions.

02

Multimodal Understanding

Learn to integrate visual, linguistic, and other sensory information to understand complex real-world phenomena.

03

Intelligent Systems

Develop autonomous systems that combine perception, reasoning, and decision-making to interact effectively with dynamic environments.

Publications

View all
Visual summary for G-MAD: A Game-Based Data Generation Framework for Multi-View RGB-T Aerial Object Detection
Conference CORE A* | CCF A Object DetectionRGB-TMulti-ViewBenchmark

G-MAD: A Game-Based Data Generation Framework for Multi-View RGB-T Aerial Object Detection

Yechan Kim✝, JongHyun Park, Dongho Yoon, Namhoon Jung, Moongu Jeon

ACM International Conference on Multimedia (MM)

Paper Supp. Material (Arxiv) Code Dataset
Visual summary for NSegment: Label-specific Deformations for Remote Sensing Image Segmentation
Journal Q1 Semantic SegmentationLabel Uncertainty

NSegment: Label-specific Deformations for Remote Sensing Image Segmentation

Yechan Kim✝, Dongho Yoon, SooYeon Kim, Moongu Jeon✝

IEEE Geoscience and Remote Sensing Letters (GRSL)

Paper Supp. Material (Arxiv) Code
Visual summary for NBBOX: Noisy Bounding Box Improves Remote Sensing Object Detection
Journal Q1 Object DetectionLabel Uncertainty

NBBOX: Noisy Bounding Box Improves Remote Sensing Object Detection

Yechan Kim✝, SooYeon Kim, Moongu Jeon✝

IEEE Geoscience and Remote Sensing Letters (GRSL)

Paper Supp. Material (Arxiv) Code

Latest writing

Read all notes