atlas

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

Occlusion-Free Face Alignment: Deep Regression Networks Coupled With De-Corrupt AutoEncoders

CVPR 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 104 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 de-corrupt autoencoders to the cascaded deep regression network (ablation)CDRN face alignment · OCFWNRMSE CDF: up to 10% when NRMSE is 0.05Helped
Add de-corrupt autoencoders to the cascaded deep regression network (ablation)CDRN face alignment · COFWNRMSE CDF: up to 6% when NRMSE is 0.10Helped
Add de-corrupt autoencoders to the cascaded deep regression network (ablation)CDRN face alignment · IBUGNRMSE CDFHelped
Use DRDA instead of OC [13]Face alignment · COFW test setmean error: 7.46(×10−2) -> 6.46(×10−2)Helped
Use DRDA instead of CoR [12]Face alignment · COFW test setmean error: 7.30(×10−2) -> 6.46(×10−2)Helped
Use DRDA instead of LBFFace alignment · IBUGmean error: 11.98% -> 10.79%Helped
Recover occluded appearance and use it together with non-occluded appearance instead of discarding occluded partsDRDA face alignment · COFWocclusion detection precision/recallHelped

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