Two-Stage Separable Adversarial Distortion-Based Robust Watermarking Framework for Diffusion Tensor Imaging

Long Zheng, Zhi Li*, Zhangyu Liu, Dandan Li, Li Zhang, Hong Yue, Fei Cheng, Qin Mao, Xuekai Wei, Mingliang Zhou

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Recent deep learning-based watermarking methods have achieved impressive results. However, they struggle with unknown distortions and often suffer from poor generalization, slow convergence, unstable training, and degraded visual quality in watermarked images. To address the above problems, this paper proposes a two-stage separable adversarial distortion (TSAD)-based robust watermarking algorithm for diffusion tensor imaging (DTI). The algorithm uses a noise-free end-to-end network in the first stage for learning and training DTI images. In the second stage, it fixes the watermark embedding network trained in the first stage, interacts the noise distortion network with the watermark extraction network to perform adversarial training for improving robustness. Experimental results show that our method achieves comparable or better robustness to seen distortions and better robustness to unseen distortions, along with enhanced stability, faster convergence, and improved visual quality in watermarked DTI images.

Original languageEnglish
Article number2454011
JournalInternational Journal of Pattern Recognition and Artificial Intelligence
Volume38
Issue number7
DOIs
Publication statusPublished - 2024
Externally publishedYes

Keywords

  • adversarial training
  • Deep learning
  • DTI
  • robust blind watermarking

Fingerprint

Dive into the research topics of 'Two-Stage Separable Adversarial Distortion-Based Robust Watermarking Framework for Diffusion Tensor Imaging'. Together they form a unique fingerprint.

Cite this