Hui-Po Wang

Hui-Po Wang

Ph.D. Candidate
CISPA – Helmholtz Center for Information Security
hui.wang [at] cispa.saarland

I am a second-year Ph.D. student with Mario Fritz at CISPA, Germany. My research interest lies in trustworthy and federated machine learning.

Before joining CISPA, I was a reserch internship in Max-Planck Institute for Informatics, Germany, where I knew my current supervisor Mario Fritz. Prior to that, I worked with Wen-Hsiao Peng and Wei-Chen Chiu in National Chiao Tung University, Taiwan.

News

October, 2022
Our work ProgFed is accepted by ICML 2022.
June, 2021
Invited to give a talk on HijackGAN at Responsible Computer Vision, CVPRw 2021.
March, 2021
Our work HijackGAN is accepted by CVPR 2021.
March, 2021
Our work MIMO-VRN is accepted by CVPR 2021.
March, 2021
Our work InfoScrub is accepted by FA.DE.TR.CV, CVPRw 2021.

Publications

ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training

Hui-Po Wang, Sebastian U. Stich, Yang He, Mario Fritz

ICML 2022

[Paper] / [Code] / [Project Page] / [Poster]

Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs

Hui-Po Wang, Ning Yu, Mario Fritz

CVPR 2021

[Paper] / [Code] / [Project Page]

Video Rescaling Networks with Joint Optimization Strategies for Downscaling and Upscaling

Yancheng Huang, Yi-Hsin Chen, Cheng-You Lu, Hui-Po Wang, Wen-Hsiao Peng, Ching-Chun Huang

CVPR 2021

[Paper] / [Code] / [Project Page]

InfoScrub: Towards Attribute Privacy by Targeted Obfuscation

Hui-Po Wang, Tribhuvanesh Orekondy, and Mario Fritz

CVPRw 2021

[Paper]

All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation

Wei-Lun Chang*, Hui-Po Wang*, Wen-Hsiao Peng, and Wei-Chen Chiu. (*euqal contribution)

CVPR 2019

[Paper] / [Code] / [Project Page]

Learning priors for adversarial autoencoders

Hui-Po Wang, Wen-Hsiao Peng, and Wei-Jan Ko

APSIPA ASC 2018 (Best Paper Award Runner-up); APSIPA T-SIP 2020

[Paper]