Geunhyeok Yu
Geunhyeok Yu
Home
Projects
Publications
Experience
Posts
Talks
Contact
CV
Light
Dark
Automatic
CVPR
A2XP: Towards Private Domain Generalization
The paper introduces A2XP, a novel approach for domain generalization, which optimizes prompts for each source domain and combines them for robust performance across domains, while also preserving privacy and integrity of the network architecture. Experimental results demonstrate its state-of-the-art performance in computer vision tasks and its potential for broader applications.
Geunhyeok Yu
,
Hyoseok Hwang
PDF
Cite
Code
Project
Poster
Slides
arXiv
Logit Standardization in Knowledge Distillation
IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024.
Geunhyeok Yu
May 9, 2024
1 min read
Paper Review
,
Seminar
Accepted to CVPR 2024 🎉
One paper accepted to CVPR 2024.
Feb 22, 2024 1:00 PM — 3:00 PM
Geunhyeok Yu
Joint Token Pruning and Squeezing Towards More Aggressive Compression of ViTs
IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024.
Geunhyeok Yu
Feb 1, 2024
1 min read
Paper Review
,
Seminar
,
Conference
Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations
IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022.
Geunhyeok Yu
Nov 19, 2023
1 min read
Paper Review
,
Seminar
,
Conference
POCO: Point Convolution for Surface Reconstruction
IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022.
Geunhyeok Yu
Aug 18, 2022
1 min read
Paper Review
,
Seminar
Density-preserving Deep Point Cloud Compression
IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022.
Geunhyeok Yu
Jun 28, 2022
1 min read
Paper Review
,
Seminar
Point Cloud Upsampling via Disentangled Refinement
IEEE/CVF Conference on Computer Vision and Pattern Recognition 2021.
Geunhyeok Yu
Jun 2, 2022
1 min read
Paper Review
,
Seminar
Cite
×