User: Guest  Login
Document type:
Konferenzbeitrag 
Author(s):
Baur, C.; Graf, R.; Wiestler, B.; Albarqouni, S.; Navab, N. 
Title:
SteGANomaly: Inhibiting CycleGAN Steganography for Unsupervised Anomaly Detection in Brain MRI 
Abstract:
Recently, it has been shown that CycleGANs are masters of steganography. They cannot only learn reliable mappings between two distributions without calling for paired training data, but can effectively hide information unseen during training in mapping results from which input data can be recovered almost perfectly. When preventing this during training, CycleGANs actually map samples much closer to the training distribution. Here, we propose to leverage this effect in the context of trending uns...    »
 
Keywords:
Anomaly Segmentation,Anomaly Detection,Unsupervised,CycleGAN,Style Transfer,Brain MRI,Brainweb,Simulated Data,Steganography,SteGANomaly,GAN,Generative Adversarial Network,Deep Learning,MICCAI 
Book / Congress title:
International Conference on Medical Image Computing and Computer-Assisted Intervention 
Organization:
Springer 
Year:
2020 
Pages:
718--727