AI Paper Atlas

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

Revisiting Coding-Based Approaches to Overcome the Curse of Dimensionality in Learning-Based Watermarking

Yupeng Qiu, Han Fang, Ee-Chien Chang

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning

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
replace correlated projection with orthogonal projection (MSE loss) (ablation)OrthoMark SED · 64-bit, 15 distortionsPSNR (dB) / average accuracy: PSNR 32.41 -> 39.20; AVG 93.82 -> 99.45Improved
replace MSE loss with QIM-style loss under orthogonal projection (ablation)OrthoMark SED · 64-bit, 15 distortionsPSNR (dB): 39.20 -> 39.26; AVG 99.45 -> 99.59Improved
replace MSE loss with QIM-style loss under correlated projection (ablation)OrthoMark SED · 64-bit, 15 distortionsaverage accuracy: 93.82 -> 92.02Hurt
use QIM-style loss instead of MSE for large payloads (ablation)OrthoMark SED · bit accuracy vs payload (clean)bit decoding accuracyImproved
use orthogonal instead of correlated projection for capacity scaling (ablation)OrthoMark SED · bit accuracy vs payload (clean)bit decoding accuracyImproved
increase inference optimization iterations from 500 to 4500 (ablation)OrthoMark · 64-bit, 15 distortionsPSNR (dB): 37.40 -> 39.71Improved
increase inference optimization iterations beyond 1000 (ablation)OrthoMark · 64-bit, 15 distortionsaverage accuracy: 99.45 -> 99.47No clear effect
use OrthoMark instead of deep watermarking baselines at 256 bitsOrthoMark · 256-bit, 15 distortionsaverage accuracy (%): 84.62 (CIN) -> 90.60Improved

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