# Meta-FC: Meta-Learning with Feature Consistency for Robust and Generalizable Watermarking

arXiv: https://arxiv.org/abs/2602.21849 · HTML: https://mlsanity.com/paper/2602.21849/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Builds on (most cited first, 20 of 20)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [StegaStamp: Invisible Hyperlinks in Physical Photographs](https://mlsanity.com/paper/1904.05343/) (2019)
- [EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection](https://mlsanity.com/paper/2312.08883/) (2023)
- [MBRS : Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compression](https://mlsanity.com/paper/2108.08211/) (2021)
- [Watermarking Images in Self-Supervised Latent Spaces](https://mlsanity.com/paper/2112.09581/) (2021)
- [Unsupervised Learning via Meta-Learning](https://mlsanity.com/paper/1810.02334/) (2018)
- [Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms](https://mlsanity.com/paper/2212.12678/) (2022)
- [ReDMark: Framework for Residual Diffusion Watermarking on Deep Networks](https://mlsanity.com/paper/1810.07248/) (2018)
- [Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning](https://mlsanity.com/paper/2012.04324/) (2020)
- [Meta Gradient Adversarial Attack](https://mlsanity.com/paper/2108.04204/) (2021)
- [SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detection](https://mlsanity.com/paper/2305.06321/) (2023)
- [InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance](https://mlsanity.com/paper/2411.07795/) (2024)
- [Practical Deep Dispersed Watermarking with Synchronization and Fusion](https://mlsanity.com/paper/2310.14532/) (2023)
- [De-END: Decoder-driven Watermarking Network](https://mlsanity.com/paper/2206.13032/) (2022)
- [Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks](https://mlsanity.com/paper/2404.03340/) (2024)
- [MLDGG: Meta-Learning for Domain Generalization on Graphs](https://mlsanity.com/paper/2411.12913/) (2024)
- [Sim-to-Real: An Unsupervised Noise Layer for Screen-Camera Watermarking Robustness](https://mlsanity.com/paper/2504.18906/) (2025)

## Abstract (arXiv)

Deep learning-based watermarking has made remarkable progress in recent years. To achieve robustness against various distortions, current methods commonly adopt a training strategy where a underlinesingle underlinerandom underlinedistortion (SRD) is chosen as the noise layer in each training batch. However, the SRD strategy treats distortions independently within each batch, neglecting the inherent relationships among different types of distortions and causing optimization conflicts across batches. As a result, the robustness and generalizability of the watermarking model are limited. To address this issue, we propose a novel training strategy that enhances robustness and generalization via underlinemeta-learning with underlinefeature underlineconsistency (Meta-FC). Specifically, we randomly sample multiple distortions from the noise pool to construct a meta-training task, while holding out one distortion as a simulated ``unknown'' distortion for the meta-testing phase. Through meta-learning, the model is encouraged to identify and utilize neurons that exhibit stable activations across different types of distortions, mitigating the optimization conflicts caused by the random sampling of diverse distortions in each batch. To further promote the transformation of stable activations into distortion-invariant representations, we introduce a feature consistency loss that constrains the decoded features of the same image subjected to different distortions to remain consistent. Extensive experiments demonstrate that, compared to the SRD training strategy, Meta-FC improves the robustness and generalization of various watermarking models by an average of 1.59%, 4.71%, and 2.38% under high-intensity, combined, and unknown distortions.