Home Mathematics Chapter 7 Enhanced image watermarking through cross-attention and noise-invariant domain learning
Chapter
Licensed
Unlicensed Requires Authentication

Chapter 7 Enhanced image watermarking through cross-attention and noise-invariant domain learning

  • Agnibh Dasgupta and Xin Zhong
Become an author with De Gruyter Brill
Explore this Subject How to publish with us
Imaging Science
This chapter is in the book Imaging Science

Abstract

Image watermarking deals with embedding and extracting watermarks in a cover image, focusing on improving generalization and robustness against various manipulations. Recent deep learning methods enhance these aspects mainly using convolutional techniques for embedding and including targeted augmentations during training. Vision transformers, known for their self-attention mechanism, efficiently handle longrange dependencies and global context, showing promise for image watermarking. However, their potential for watermark embedding, especially using cross-attention, has not been fully explored. This study introduces a robust image watermarking approach utilizing cross-attention and invariant domain learning, presenting two significant advancements. First, we propose a watermark embedding method based on a multihead cross-attention mechanism. This mechanism enables an effective exchange of information between the cover image and the watermark, pinpointing the best spots for embedding based on semantic relevance. Second, we suggest learning a domain representation that is invariant to both semantic shifts and noise, potentially broadening the scope for improving image watermarking techniques.

Abstract

Image watermarking deals with embedding and extracting watermarks in a cover image, focusing on improving generalization and robustness against various manipulations. Recent deep learning methods enhance these aspects mainly using convolutional techniques for embedding and including targeted augmentations during training. Vision transformers, known for their self-attention mechanism, efficiently handle longrange dependencies and global context, showing promise for image watermarking. However, their potential for watermark embedding, especially using cross-attention, has not been fully explored. This study introduces a robust image watermarking approach utilizing cross-attention and invariant domain learning, presenting two significant advancements. First, we propose a watermark embedding method based on a multihead cross-attention mechanism. This mechanism enables an effective exchange of information between the cover image and the watermark, pinpointing the best spots for embedding based on semantic relevance. Second, we suggest learning a domain representation that is invariant to both semantic shifts and noise, potentially broadening the scope for improving image watermarking techniques.

Chapters in this book

  1. Frontmatter I
  2. Preface V
  3. Contents VII
  4. Section: Image processing
  5. Chapter 1 Magnetic resonance image re-parameterization on real data 1
  6. Chapter 2 Denoising and gradient fusion for effective edge detection for noisy color images 17
  7. Chapter 3 Understanding driver attention to objects for ADASs: what do drivers see? 39
  8. Chapter 4 Image clustering enhanced with refined image classification 59
  9. Chapter 5 AI-powered framework for objective scoring of product design innovation 89
  10. Section: Computer vision
  11. Chapter 6 Image inpainting using GAN transformerbased model 111
  12. Chapter 7 Enhanced image watermarking through cross-attention and noise-invariant domain learning 127
  13. Chapter 8 Online melt pool monitoring using a deep transformer image processing solution 153
  14. Chapter 9 Implementation of deep learning techniques on thermal image classification 173
  15. Chapter 10 Drishti: a generative AI-based application for gesture recognition and execution 203
  16. Section: Pattern recognition
  17. Chapter 11 Exploring muzzle biometrics: a deep learning framework for noninvasive cattle recognition 239
  18. Chapter 12 Utilizing real-world data to develop a userindependent sensor-based human activity recognition system 253
  19. Index 273
https://doi.org/10.1515/9783111436425-007

Chapters in this book

  1. Frontmatter I
  2. Preface V
  3. Contents VII
  4. Section: Image processing
  5. Chapter 1 Magnetic resonance image re-parameterization on real data 1
  6. Chapter 2 Denoising and gradient fusion for effective edge detection for noisy color images 17
  7. Chapter 3 Understanding driver attention to objects for ADASs: what do drivers see? 39
  8. Chapter 4 Image clustering enhanced with refined image classification 59
  9. Chapter 5 AI-powered framework for objective scoring of product design innovation 89
  10. Section: Computer vision
  11. Chapter 6 Image inpainting using GAN transformerbased model 111
  12. Chapter 7 Enhanced image watermarking through cross-attention and noise-invariant domain learning 127
  13. Chapter 8 Online melt pool monitoring using a deep transformer image processing solution 153
  14. Chapter 9 Implementation of deep learning techniques on thermal image classification 173
  15. Chapter 10 Drishti: a generative AI-based application for gesture recognition and execution 203
  16. Section: Pattern recognition
  17. Chapter 11 Exploring muzzle biometrics: a deep learning framework for noninvasive cattle recognition 239
  18. Chapter 12 Utilizing real-world data to develop a userindependent sensor-based human activity recognition system 253
  19. Index 273
Sign up now to receive a 20% welcome discount
Institutional Access
How does access work?
Have an idea on how to improve our website?
Please write us.
© 2025 De Gruyter Brill
Downloaded on 20.11.2025 from https://www.degruyterbrill.com/document/doi/10.1515/9783111436425-007/html
Scroll to top button