← Search

Xiaowei Dong

2 accepted papers

2023

Towards Fairness-aware Adversarial Network Pruning

ICCV 2023poster

Network pruning aims to compress models while minimizing loss in accuracy. With the increasing focus on bias in AI systems, the bias inheriting or even magnification nature of traditional network pruning methods has raised a new perspective towards fairness-aware network pruning. Straightforward pru…

Cited by 8PDFScholar
2022

Fairness-Aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models

CVPR 2022poster

Prioritizing fairness is of central importance in artificial intelligence (AI) systems, especially for those societal applications, e.g., hiring systems should recommend applicants equally from different demographic groups, and risk assessment systems must eliminate racism in criminal justice. Exist…

Cited by 75PDFScholar