AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Dataset Ownership Verification for Pre-trained Masked Models

Yuechen Xie, Jie Song, Yicheng Shan, Xiaoyan Zhang, Yuanyu Wan, Shengxuming Zhang, Jiarui Duan, Mingli Song

ICCV 2025 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Masked autoencoder pretraining · 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
compute the t-test on relative difficulty delta R instead of raw difficulty R (ablation)DOV4MM · ImageNet-1K, SimMIM Swin-Bp-value: 0.10 -> 0.03Improved
increase decoder training set D_t from 10,000 to 20,000 images (ablation)DOV4MM · ImageNet-1K, CAE ViT-B/16p-value: 0.02 -> 10^-3Improved
increase sampling iterations K from 10 to 30 (ablation)DOV4MM · ImageNet-1K, CAE ViT-B/16p-value: 0.05 -> 10^-3Improved
increase samples per iteration N from 256 to 4,096 (ablation)DOV4MM · ImageNet-1K, MAE ViT-B/16p-value: 0.02 -> 10^-18Improved
vary decoder width, depth and heads (ablation)DOV4MM · ImageNet-1K, MAE/CAE/iBOTp-valueNo clear effect
vary masking ratio from 30% to 90% (ablation)DOV4MM · ImageNet-1K, MAE/CAE/iBOTp-value: CAE 10^-3 -> 0.04 at 90%No clear effect
fine-tune suspicious ViT-L/16 iBOT on Places365 downstream taskDOV4MM · ImageNet-1K pretrained, fine-tunedp-value: 10^-3 -> 0.01No clear effect
add early stopping (patience=15) to suspect trainingDOV4MM · ImageNet-100, MAE ViT-L/16p-value: 10^-6 -> 10^-4No clear effect
add adaptive-attack loss L that narrows seen/unseen reconstruction gapDOV4MM · ImageNet-50, CAEp-value: 10^-10 -> 10^-8No clear effect

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