AI Paper Atlas

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

Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency

Xingyi Zhou, Arjun Karpur, Chuang Gan, Linjie Luo, Qixing Huang

ECCV 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 42 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 view-consistency term (ablation)full method · Redwood depth (chair)average distance error (%): 13.95 -> 12.76Improved
add view-consistency term (ablation)full method · ShapeNet (chair)average distance error (%): 6.70 -> 6.60Improved
add geometric alignment term (ablation)full method · Redwood depth (chair)average distance error (%): 12.97 -> 12.76Improved
add geometric alignment term (ablation)full method · ShapeNet (chair)average distance error (%): 6.67 -> 6.60Improved
update latent configurations by alternating minimization instead of re-initializing (ablation)full method · Redwood depth (chair)average distance error (%): 13.43 -> 12.76Improved
update latent configurations by alternating minimization instead of re-initializing (ablation)full method · ShapeNet (chair)average distance error (%): 6.66 -> 6.60Improved
use proposed adaptation instead of ADDAResNet50 keypoint predictor · Redwood depth (chair)average distance error (%): 15.44 -> 12.76Improved
use proposed adaptation instead of ADDAResNet50 keypoint predictor · ShapeNet (chair)average distance error (%): 6.98 -> 6.60Improved
apply ADDA instead of no adaptationResNet50 keypoint predictor · 3DCNN depth (chair)average distance error (%): 11.61 -> 11.81No clear effect
apply proposed domain adaptationResNet50 keypoint predictor · Redwood depth (chair)average distance error (%): 16.01 -> 12.76Improved
apply proposed domain adaptationResNet50 keypoint predictor · Redwood RGB (chair)average distance error (%): 27.59 -> 25.24Improved
apply proposed adaptation to motorcycle keypointsResNet50 keypoint predictor · Redwood depth (motorcycle)average distance error (%): 21.55% -> 18.92%Improved

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