Oriel — AI & technology worth noticing, every day.

Out-of-distribution AI-generated image detection with zero-phase deconvolution for residual whitening

Paper · https://arxiv.org/abs/2611.00043

arXiv:2611.00043v1 Announce Type: new Abstract: Current AI-generated image detection methods struggle in out-of-distribution testing conditions because detectors are usually not robust when evaluated on generators not included in the training set. This work explores a way to mitigate the forensic bias between sources of images -whether real or generated -by removing generator-specific fingerprints. This new training process can be approximated by pre-processing involving a deconvolution operation designed to remove correlated noise patterns inducing loss of generalization. Indeed, we show that whitening the spatial distribution of the image noise residuals can significantly improve the performance of detectors on images coming from generators unseen during training. In particular, an end-to-end CNN model trained on whitened image residuals improves detection by 12.6% on average compared to a training involving original images.

First seen by Oriel on .

No saved summary available.

Aliases

SourceExternal IDURL
arXiv AI Papersoai:arXiv.org:2611.00043v1https://arxiv.org/abs/2611.00043 Read discussion