AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Differentially Private 2D Human Pose Estimation

Kaushik Bhargav Sivangi, Paul Henderson, Fani Deligianni

CVPR 2026 · Federated learning and privacy › Differential privacy · approach: Private data analysis frameworks · 4 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 subspace projection to DP-SGD (ablation)DP-SGD finetuning · MPII (C=0.01, eps=0.2)mean PCKh@0.5: 63.85 -> 78.48Improved
add subspace projection to DP-SGD (ablation)DP-SGD finetuning · MPII (C=0.01, eps=0.8)mean PCKh@0.5: 78.17 -> 80.63Improved
add subspace projection to DP-SGD (ablation)DP-SGD training from scratch · MPII (C=0.1)mean PCKh@0.5: 9.80 -> 13.05Improved
add subspace projection to DP-SGD (ablation)DP-SGD finetuning from scratch · MPII (C=0.1)mean PCKh@0.5No clear effect
add feature-level privacy (FDP) to DP-SGD (ablation)DP-SGD finetuning · MPII (C=0.01, eps=0.2)mean PCKh@0.5: 63.85 -> 75.46Improved
add feature-level privacy (FDP) to DP-SGD (ablation)DP-SGD finetuning · MPII (C=0.01, eps=0.8)mean PCKh@0.5: 78.17 -> 80.40Improved
combine feature-level privacy and subspace projection (vs DP-SGD) (ablation)DP-SGD finetuning · MPII (C=1.0, eps=0.8)mean PCKh@0.5: 12.53 -> 71.66Improved
combine feature-level privacy and subspace projection (vs FDP alone) (ablation)FDP training from scratch · MPII (C=0.1, eps=0.8)mean PCKh@0.5: 11.22 -> 33.48Improved
combine feature-level privacy and subspace projection (vs DP-SGD) (ablation)DP-SGD training from scratch · MPII (C=0.1, eps=0.8)mean PCKh@0.5: 6.85 -> 33.48Improved
lower clipping threshold from C=0.1 to C=0.01 (ablation)DP-SGD finetuning · MPII (eps=0.2)mean PCKh@0.5: 28.46 -> 63.85Improved
lower clipping threshold from C=1.0 to C=0.01 (ablation)DP-SGD finetuning · MPII (eps=0.2)mean PCKh@0.5: 5.94 -> 63.85Improved
apply DP updates to a frozen backbone instead of finetuning from scratchFeature-Projective DP · HumanARTAP: 69.5 -> 63.3 non-private; reverses under DPMixed

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