Robust Image Watermarking based on Cross-Attention and Invariant Domain Learning
This addresses the problem of enhancing watermark robustness for image security applications, presenting a novel approach rather than incremental improvements.
The paper tackles robust image watermarking by introducing a method using cross-attention for embedding and invariant domain learning, resulting in improved generalization and robustness without specifying concrete numbers.
Image watermarking involves embedding and extracting watermarks within a cover image, with deep learning approaches emerging to bolster generalization and robustness. Predominantly, current methods employ convolution and concatenation for watermark embedding, while also integrating conceivable augmentation in the training process. This paper explores a robust image watermarking methodology by harnessing cross-attention and invariant domain learning, marking two novel, significant advancements. First, we design a watermark embedding technique utilizing a multi-head cross attention mechanism, enabling information exchange between the cover image and watermark to identify semantically suitable embedding locations. Second, we advocate for learning an invariant domain representation that encapsulates both semantic and noise-invariant information concerning the watermark, shedding light on promising avenues for enhancing image watermarking techniques.