Meta-FC：基于特征一致性的元学习用于鲁棒且可泛化的水印
Meta-FC: Meta-Learning with Feature Consistency for Robust and Generalizable Watermarking
把元学习加特征一致性损失当作一种可插拔的训练策略，用来替代单随机失真（SRD）噪声层，可直接迁移到其他需要抵抗多种失真的视觉任务（如复原、隐写、对抗训练）中，缓解批次间优化冲突。
原文依据 we propose a novel training strategy that enhances robustness and generalization via meta-learning with feature consistency
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近年来，基于深度学习的水印技术取得了显著进展。为获得对各种失真的鲁棒性，现有方法通常采用一种训练策略，即在每个训练批次中选取单一随机失真（SRD）作为噪声层。然而，SRD 策略在每个批次内独立地处理各种失真，忽略了不同失真类型之间的内在联系，并在批次之间造成优化冲突。为解决该问题，我们提出一种新的训练策略，通过带特征一致性的元学习（Meta-FC）来增强鲁棒性与泛化能力。具体而言，我们从噪声池中随机采样多种失真以构建元训练任务，同时留出一种失真作为模拟的“未知”失真用于元测试阶段。通过元学习，模型被促使去识别并利用在不同失真类型下表现出稳定激活的神经元，从而缓解每个批次中随机采样多种失真所导致的优化冲突。为进一步促进稳定激活转化为失真不变的表征，我们引入特征一致性损失，约束同一图像在不同失真下解码得到的特征保持一致。大量实验表明，与 SRD 训练策略相比，Meta-FC 在高强度、组合以及未知失真下将各类水印模型的鲁棒性与泛化能力平均提升 1.59%、4.71% 和 2.38%。代码已开源于 https://github.com/007-li/Meta-FC。
英文原文摘要 1752 字符
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 s ingle \underline r andom \underline 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. To address this issue, we propose a novel training strategy that enhances robustness and generalization via \underline meta -learning with \underline f eature \underline 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. Code has been made \href https://github.com/007-li/Meta-FC open-source .