.png){kind=icon}
返回
MCFN: Multi-scale Crossover Feed-forward Network for high performance watermarking
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2024.129282.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In recent years, deep learning-based watermarking for digital images has seen substantial progress, particularly in embedding secret messages in an invisible manner and extracting them after attacks. However, existing methods face challenges ineffectively integrating spatial and frequency domain features, which limits overall performance. To address this, we propose the Multi-scale Crossover Feed-forward Network (MCFN), an innovative solution explicitly designed to process features of secret messages and cover images in a robust watermarking framework. The MCFN features a crossover structure that facilitates global communication between single-dimensional and double-dimensional features, enhancing the capacity to simultaneously capture crucial characteristics from both secret messages and cover images. A key element of our design is the Discrete Wavelet Transform (DWT) convolution block, which enables multi-scale feature extraction in the frequency domain, overcoming the limitations of conventional watermarking networks. We also incorporate perceptual loss to ensure high visual quality of the watermarked image and introduce a Bi-Directional Attack Simulation Layer (BD-ASL) to improve resilience against various attacks during training. Extensive experimental results validate that our framework achieves superior capacity, robustness, and imperceptibility, significantly outperforming current state-of-the-art methods in the deep learning-based watermarking field.
Keyword:
DWT convolution block
Perceptual loss
BD-ASL
Multi-scale Crossover Feed-forward network
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
ReDMark: Framework for residual diffusion watermarking based on deep networksReDMark: 基于深度网络的残差扩散水印框架
PREAI
分享收藏The Preparation of High-Volume Fraction SiC/Al Composites with High Thermal Conductivity by Vacuum Pressure Infiltration.png)
Crystals
OAAI
CrystalsIF0
OAAI分享收藏MultiCut-MultiMix: a two-level data augmentation method for detecting small and densely distributed objects in large-size imagesVISUAL COMPUTER
VISUAL COMPUTERIF2.9
PREAI
分享收藏分享收藏Two-dimensional bricklayer arrangements of tolans using halogen bonding interactions使用卤素键相互作用的tolans的二维瓦工层布置
PREAI
分享收藏
查看更多内容