Logo image
Back
E3: Ensemble of Expert Embedders for Adapting Synthetic Image Detectors to New Generators Using Limited Data
Conference proceeding   Open access

E3: Ensemble of Expert Embedders for Adapting Synthetic Image Detectors to New Generators Using Limited Data

Aref Azizpour, Tai D. Nguyen, Manil Shrestha, Kaidi Xu, Edward Kim and Matthew C. Stamm
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp 4334-4344
17 Jun 2024
DOI: https://doi.org/10.1109/CVPRW63382.2024.00437
url
https://arxiv.org/abs/2404.08814View
Submitted Open arXiv.org - Non-exclusive license to distribute

Abstract

Accuracy Continuing education Contniual Learning Forensics Knowledge engineering Multimedia Forensics Synthetic Image Detection Synthetic Images Training Training data Transfer learning Transformers
As generative AI progresses rapidly, new synthetic image generators continue to emerge at a swift pace. Traditional detection methods face two main challenges in adapting to these generators: the forensic traces of synthetic images from new techniques can vastly differ from those learned during training, and access to data for these new generators is often limited. To address these issues, we introduce the Ensemble of Expert Embedders (E3), a novel continual learning framework for updating synthetic image detectors. E3 enables the accurate detection of images from newly emerged generators using minimal training data. Our approach does this by first employing transfer learning to develop a suite of expert embedders, each specializing in the forensic traces of a specific generator. Then, all embeddings are jointly analyzed by an Expert Knowledge Fusion Network to produce accurate and reliable detection decisions. Our experiments demonstrate that E3 outperforms existing continual learning methods, including those developed specifically for synthetic image detection.

Metrics

11 Record Views
1 citations in Scopus

Details

Logo image