Text-Guided Image Invariant Feature Learning for Robust Image Watermarking
This work addresses robustness in image watermarking for content integrity, representing an incremental improvement over existing self-supervised learning methods by incorporating text guidance.
The paper tackles the problem of robust image watermarking by proposing a text-guided invariant feature learning framework that uses CLIP's text embeddings as semantic anchors to enforce feature invariance under distortions, achieving higher cosine similarity in feature consistency tests and outperforming existing watermarking schemes in extraction accuracy under severe distortions.
Ensuring robustness in image watermarking is crucial for and maintaining content integrity under diverse transformations. Recent self-supervised learning (SSL) approaches, such as DINO, have been leveraged for watermarking but primarily focus on general feature representation rather than explicitly learning invariant features. In this work, we propose a novel text-guided invariant feature learning framework for robust image watermarking. Our approach leverages CLIP's multimodal capabilities, using text embeddings as stable semantic anchors to enforce feature invariance under distortions. We evaluate the proposed method across multiple datasets, demonstrating superior robustness against various image transformations. Compared to state-of-the-art SSL methods, our model achieves higher cosine similarity in feature consistency tests and outperforms existing watermarking schemes in extraction accuracy under severe distortions. These results highlight the efficacy of our method in learning invariant representations tailored for robust deep learning-based watermarking.