AI-Vision Lab
Division of Intelligent Robot @ DGIST
Embedded Files
Goal
Goal
Our lab aims to address computer vision challenges across diverse domains—including natural images, medical imaging, and industrial scenes—by leveraging state-of-the-art AI technologies. We are dedicated to designing novel models, extracting meaningful information from data, and conducting in-depth analysis to solve real-world problems. Through these efforts, we strive to build intelligent systems that can robustly interpret complex visual environments and contribute to both scientific advancement and societal impact.
Notice
Notice
We are looking for self-motivated students who are interested in AI and vision fields. Feel free to contact soopilkim@dgist.ac.kr.
저희 연구실은 함께 연구할 대학원생, 인턴, 학부 연구원을 모집하고 있습니다. 컴퓨터 비전 또는 인공지능 기술에 관심 있는 분들의 많은 지원을 환영합니다. 연구 참여나 면담을 희망하시는 분은 soopilkim@dgist.ac.kr 로 연락 주세요.
News
News
2025.08 We will be presenting our research paper "Logical Anomaly Detection with Text-Based Logic via Component-Aware Contrastive Language-Image Training" @ SIGKDD.
2025.07 AI-Vision Lab has been established.
Research Topics
Research Topics
Few-Shot Image Segmentation
Few-Shot Image Segmentation
Label-efficient segmentation of natural, medical, and industrial images using various machine learning techniques.
Meta learning
Semi-supervised learning
In context regularization
Visual Anomaly Detection
Visual Anomaly Detection
Structural anomaly detection
Logical anomaly detection
Federated Learning
Federated Learning
Federated learning with heterogeneous data
Federated learning for multi-organ segmentation
Communication-efficient federated learning
Vision-Language Models
Vision-Language Models
CLIP based anomaly detection
Language-guided image segmentation
Foundation models
Industrial Anomaly Detection
Vision-Language Models
Image Segmentation & Classification
Medical Image Analysis
Few-Shot Learning
Meta Learning
Federated Learning
Page updated
Google Sites
Report abuse