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.

翻译：图像水印涉及在载体图像中嵌入和提取水印，深度学习方法逐渐兴起以增强泛化性和鲁棒性。当前主流方法主要采用卷积与拼接操作实现水印嵌入，同时在训练过程中整合可预见的增强手段。本文探索了一种利用交叉注意力机制与不变域学习的鲁棒图像水印方法，标志着两项新颖且重要的进展。首先，我们设计了基于多头交叉注意力机制的水印嵌入技术，能够实现载体图像与水印之间的信息交互，从而识别语义上适宜的嵌入位置。其次，我们倡导学习一个包含水印相关语义信息与噪声不变信息的不变域表征，为改进图像水印技术揭示了具有前景的研究方向。