AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

HamiPose: Hamiltonian Optimization for Unsupervised Domain Adaptive Pose Estimation

Jiawen Li, Fei Jiang, Dandan Zhu, Aimin Zhou

CVPR 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation

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 unified metric (model-wide mass with head-level normalizer) (ablation)Mean Teacher baseline · SURREAL->Human3.6MPCK@0.05 All: 75.3 -> 77.2Improved
add unified metric (ablation)Mean Teacher baseline · RHD->H3DPCK@0.05 All: 79.3 -> 80.9Improved
add channelwise gated filtering on top of unified metric (ablation)Mean Teacher + unified metric · SURREAL->Human3.6MPCK@0.05 All: 77.2 -> 78.5Improved
add channelwise gated filtering on top of unified metric (ablation)Mean Teacher + unified metric · RHD->H3DPCK@0.05 All: 80.9 -> 82.3Improved
add Hamiltonian symplectic transport (ablation)Mean Teacher + metric + filtering · SURREAL->Human3.6MPCK@0.05 All: 78.5 -> 79.8Improved
add Hamiltonian symplectic transport (ablation)Mean Teacher + metric + filtering · RHD->H3DPCK@0.05 All: 82.3 -> 83.1Improved
use keypointwise gating instead of unified gating (ablation)HamiPose gradient filter · UDA trainingsource-target gradient conflict ratio at epoch 30: 8 to 9% -> 6%Improved
use Hamiltonian optimizer instead of SGD or Adam (ablation)HamiPose training · UDA training losstraining loss stabilityMixed
use moderate gamma_max (2.0) with 10% warmup ratio, gamma_min 0 (ablation)channelwise gate · RHD->H3DPCK@0.05: 68.0 -> 70.3 (gamma_max 1.0 5% warmup vs 2.0 10% warmup)Improved
start gate sharpness gamma_min at 0 instead of 0.5 (ablation)channelwise gate · RHD->H3DPCK@0.05: 69.7 -> 70.3Improved
use overly long warmup ratio (20%) instead of 10% (ablation)channelwise gate · RHD->H3DPCK@0.05: 70.3 -> 69.5Hurt
apply HamiPose to domain generalization (train SURREAL->LSP, test Human3.6M)HamiPose · Human3.6M (unseen)PCK@0.05 All: 76.8 -> 77.5 vs GGAImproved

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