AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

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

Yuheng Li, Weitong Chen, Chengcheng Zhu, Jiale Zhang, Chunpeng Ge, Di Wu, Guodong Long

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add meta-train/meta-test and feature consistency vs SRD (ablation)Watermark models · Combined distortions (Table 4)bit accuracy (%): 87.94 -> 92.65Improved
add meta-test phase on top of meta-train and FC (ablation)Meta-FC · Combined distortions (Table 4)bit accuracy (%): 91.09 -> 92.65Improved
add meta-test phase on top of meta-train and FC (ablation)Meta-FC · High-intensity distortions (Table 4)bit accuracy (%): 95.85 -> 95.93No clear effect
add feature consistency loss (ablation)Meta-FC · Combined distortions (Table 4)bit accuracy (%): 90.44 -> 92.65Improved
add feature consistency loss (ablation)Meta-FC · Unknown distortions (Table 4)bit accuracy (%): 90.99 -> 90.93No clear effect
add meta-train phase (vs meta-test only) (ablation)Meta-FC · Combined distortions (Table 4)bit accuracy (%): 90.58 -> 92.65Improved
train with Meta-FC instead of SRDMBRS · DIV2K, combined distortionsbit accuracy (%): 77.10 -> 84.84Improved
train with Meta-FC instead of SRDSepMark · DIV2K, combined distortionsbit accuracy (%): 81.14 -> 93.85Improved
train with Meta-FC instead of SRDStegaStamp · DIV2K, high-intensity distortionsbit accuracy (%): 94.48 -> 95.57Improved
train with Meta-FC instead of SRDFIN · DIV2K, unknown distortionsbit accuracy (%): 86.25 -> 87.23Improved
train with Meta-FC instead of SRD on Brightness (high-intensity)MBRS · DIV2K, high-intensity Brightnessbit accuracy (%): 94.25 -> 93.93Hurt
Meta-FC instead of SRD training costStegaStamp · training timehours: 1.81 -> 2.36Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy