Search Results for author: Dohoon Kim

Found 4 papers, 2 papers with code

MADCluster: Model-agnostic Anomaly Detection with Self-supervised Clustering Network

no code implementations22 May 2025 Sangyong Lee, Subo Hwang, Dohoon Kim

In this paper, we propose MADCluster, a novel model-agnostic anomaly detection framework utilizing self-supervised clustering.

Anomaly Detection Clustering

MAFA: Managing False Negatives for Vision-Language Pre-training

1 code implementation CVPR 2024 Jaeseok Byun, Dohoon Kim, Taesup Moon

We consider a critical issue of false negatives in Vision-Language Pre-training (VLP), a challenge that arises from the inherent many-to-many correspondence of image-text pairs in large-scale web-crawled datasets.

Power Allocation for Device-to-Device Interference Channel Using Truncated Graph Transformers

no code implementations20 Jul 2023 Dohoon Kim, Shenghui Song

Power control for the device-to-device interference channel with single-antenna transceivers has been widely analyzed with both model-based methods and learning-based approaches.

Graph Neural Network

PU-EdgeFormer: Edge Transformer for Dense Prediction in Point Cloud Upsampling

1 code implementation2 May 2023 Dohoon Kim, Minwoo Shin, Joonki Paik

We employ graph convolution using EdgeConv, which learns the local geometry and global structure of point cloud better than existing point-to-feature method.

point cloud upsampling

Cannot find the paper you are looking for? You can Submit a new open access paper.