FairAdapter: Detecting AI-generated Images with Improved Fairness

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ding, Feng, Zhang, Jun, He, Xinan, Xu, Jianfeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910708687437824
author Ding, Feng
Zhang, Jun
He, Xinan
Xu, Jianfeng
author_facet Ding, Feng
Zhang, Jun
He, Xinan
Xu, Jianfeng
contents The high-quality, realistic images generated by generative models pose significant challenges for exposing them.So far, data-driven deep neural networks have been justified as the most efficient forensics tools for the challenges. However, they may be over-fitted to certain semantics, resulting in considerable inconsistency in detection performance across different contents of generated samples. It could be regarded as an issue of detection fairness. In this paper, we propose a novel framework named Fairadapter to tackle the issue. In comparison with existing state-of-the-art methods, our model achieves improved fairness performance. Our project: https://github.com/AppleDogDog/FairnessDetection
format Preprint
id arxiv_https___arxiv_org_abs_2411_14755
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FairAdapter: Detecting AI-generated Images with Improved Fairness
Ding, Feng
Zhang, Jun
He, Xinan
Xu, Jianfeng
Computer Vision and Pattern Recognition
Computers and Society
The high-quality, realistic images generated by generative models pose significant challenges for exposing them.So far, data-driven deep neural networks have been justified as the most efficient forensics tools for the challenges. However, they may be over-fitted to certain semantics, resulting in considerable inconsistency in detection performance across different contents of generated samples. It could be regarded as an issue of detection fairness. In this paper, we propose a novel framework named Fairadapter to tackle the issue. In comparison with existing state-of-the-art methods, our model achieves improved fairness performance. Our project: https://github.com/AppleDogDog/FairnessDetection
title FairAdapter: Detecting AI-generated Images with Improved Fairness
topic Computer Vision and Pattern Recognition
Computers and Society
url https://arxiv.org/abs/2411.14755