AI Paper Atlas

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

Rethinking Data Bias: Dataset Copyright Protection via Embedding Class-wise Hidden Bias

Jinhyeok Jang, ByungOk Han, Jaehong Kim, Chan-Hyun Youn

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 2 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 mean of target dataset mu(X) to the noise watermark when testing (ablation)Noise patch watermark · CIFAR10 (ResNet18, no flip)val acc on watermark (%): 62.14 -> 71.69Improved
apply horizontal flip augmentation to noise placement watermark (ablation)Noise patch watermark · CIFAR10 (ResNet18)val acc on watermark (%): 62.14 -> 20.26Hurt
overlay auxiliary dataset instead of noise patches (ablation)Class-wise bias embedding · CIFAR10 (ResNet18, both flips)val acc on watermark (%): 9.15 -> 69.05Improved
overlay auxiliary data at higher lambda (0.3 to 0.7) (ablation)Overlay watermark · CIFAR10 (ResNet18, no flip)val acc on benign (%): 90.47 -> 88.52Hurt
use steganography-based DWN invisible watermark rather than visible overlayUndercover bias · CIFAR10avg. SSIM: 0.9785 vs 0.9775 (Blended), 0.9202 (Radioactive)Improved
watermark training data with undercover biasDenseNet-BC · CIFAR100val acc on benign (%): 71.79 -> 68.27Hurt
watermarked training of MobileNetV2 vs cleanMobileNetV2 · ImageNetval mAcc on watermark (%): 11.90 -> 43.95Improved
use modulo pairing when target has more classes than auxiliaryUndercover bias · Tiny ImageNetval mAcc on watermark (%): 8.84 -> 34.37Improved
use 2/N_cls threshold for verificationUndercover bias · CIFAR10, CIFAR100 histogram analysisverification separationImproved

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