Paper
Meta-FC: Meta-Learning with Feature Consistency for Robust and Generalizable Watermarking
Authors
Yuheng Li, Weitong Chen, Chengcheng Zhu, Jiale Zhang, Chunpeng Ge, Di Wu, Guodong Long
Abstract
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 \underline{\textbf{s}}ingle \underline{\textbf{r}}andom \underline{\textbf{d}}istortion (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 \underline{\textbf{meta}}-learning with \underline{\textbf{f}}eature \underline{\textbf{c}}onsistency (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.
Metadata
Related papers
Fractal universe and quantum gravity made simple
Fabio Briscese, Gianluca Calcagni • 2026-03-25
POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan
Marta Moscati, Muhammad Saad Saeed, Marina Zanoni, Mubashir Noman, Rohan Kuma... • 2026-03-25
LensWalk: Agentic Video Understanding by Planning How You See in Videos
Keliang Li, Yansong Li, Hongze Shen, Mengdi Liu, Hong Chang, Shiguang Shan • 2026-03-25
Orientation Reconstruction of Proteins using Coulomb Explosions
Tomas André, Alfredo Bellisario, Nicusor Timneanu, Carl Caleman • 2026-03-25
The role of spatial context and multitask learning in the detection of organic and conventional farming systems based on Sentinel-2 time series
Jan Hemmerling, Marcel Schwieder, Philippe Rufin, Leon-Friedrich Thomas, Mire... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2602.21849v1</id>\n <title>Meta-FC: Meta-Learning with Feature Consistency for Robust and Generalizable Watermarking</title>\n <updated>2026-02-25T12:26:26Z</updated>\n <link href='https://arxiv.org/abs/2602.21849v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2602.21849v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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 \\underline{\\textbf{s}}ingle \\underline{\\textbf{r}}andom \\underline{\\textbf{d}}istortion (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 \\underline{\\textbf{meta}}-learning with \\underline{\\textbf{f}}eature \\underline{\\textbf{c}}onsistency (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.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n <published>2026-02-25T12:26:26Z</published>\n <arxiv:primary_category term='cs.CV'/>\n <author>\n <name>Yuheng Li</name>\n </author>\n <author>\n <name>Weitong Chen</name>\n </author>\n <author>\n <name>Chengcheng Zhu</name>\n </author>\n <author>\n <name>Jiale Zhang</name>\n </author>\n <author>\n <name>Chunpeng Ge</name>\n </author>\n <author>\n <name>Di Wu</name>\n </author>\n <author>\n <name>Guodong Long</name>\n </author>\n </entry>"
}