FasterCReW: Performance or Efficiency? A Lightweight Conditional Residual DNN-Based Watermarking Based on FasterNet
- 14 March 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (8) , 7732-7746
Abstract
Deep neural networks (DNNs) based watermarking algorithms have made significant strides in recent years. However, existing methods either demand substantial resources for image feature extraction during watermark embedding, sacrificing efficiency, or completely neglect image texture information, resulting in suboptimal performance. Moreover, current algorithms struggle with real-time watermark extraction. To address these limitations, we propose a lightweight conditional residual watermarking (CReW) architecture. Specifically, CReW employs a Conditional Generative Adversarial Network (CGAN) framework to generate an adaptive residual image guided by the structure of the cover image, which is decoupled from the network to reduce computational complexity. This design enables CReW to achieve an optimal balance between performance and efficiency. Additionally, by directly optimizing the residual image to capture variations in watermark behavior under distortion, CReW significantly enhances robustness. Furthermore, we design redundancy coding blocks to increase the mutual information of the watermark, along with a patch-level discriminator to improve local patch discrimination, thereby further enhancing image quality. Finally, by reducing channel redundancy and leveraging FasterNet, we developed a low-complexity network architecture, Faster-CReW, which facilitates real-time watermark embedding and extraction. Extensive experimental results demonstrate that, despite having 36× fewer network parameters and 30× fewer floating point operations (FLOPs) than Adaptor, Faster-CReW exhibits excellent robustness against distortions such as cropout, JPEG compression, and Gaussian noise. Furthermore, Faster-CReW significantly outperforms other existing DNN-based watermarking algorithms in terms of running speed, achieving an 8× speed increase over UDH and a 28× increase over Adaptor on an Intel Core i7-8750H CPU.Keywords
Funding Information
- National Natural Science Foundation of China (62402230, 62306149, 61972207, U22B2062)
- Nanjing Major Science and Technology Special Project (202405002)
- Jiangsu Basic Research Programs-Natural Science Foundation (BK20240693)
- Natural Science Research of Jiangsu Higher Education Institutions of China (24KJB520019)
- Startup Foundation for Introducing Talent of NUIST (2023r045)
- Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET) fund
- Priority Academic Program Development of Jiangsu Higher Education Institutions (PAPD) fund
This publication has 38 references indexed in Scilit:
- Conditional image-to-image translation generative adversarial network (cGAN) for fabric defect data augmentationNeural Computing and Applications, 2024
- Patch-Attention GAN: Image Translation using BiFormer and Attention Framework2024
- DITW: A High-Performance Deep-Independent Template-Based Watermarking2024
- Universal screen-shooting robust image watermarking with channel-attention in DCT domainExpert Systems with Applications, 2023
- Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks2023
- Performance optimization for cloud computing systems in the microservice era: state-of-the-art and research opportunitiesFrontiers of Computer Science, 2022
- ReDMark: Framework for residual diffusion watermarking based on deep networksExpert Systems with Applications, 2020
- Image-to-Image Translation with Conditional Adversarial Networks2017
- Microsoft COCO: Common Objects in Context2014
- Large-Scale Machine Learning with Stochastic Gradient Descent2010