AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Laplace Landmark Localization

Joseph P. Robinson, Yuncheng Li, Ning Zhang, Yun Fu, Sergey Tulyakov

ICCV 2019 · Label-efficient and robust learning › Semi-supervised learning · approach: GAN-based semi-supervised learning · 58 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
replace softargmax objective with LaplaceKL (ablation)RCN landmark detector · 300W fullNMSE: 4.25 -> 4.01Improved
replace softargmax with LaplaceKL on AFLW (ablation)RCN landmark detector · AFLWNMSE: 2.26 -> 1.97Improved
add adversarial training with 70K unlabeled MegaFace images (ablation)LaplaceKL · 300W fullNMSE: 4.01 -> 3.91Improved
add adversarial training with 70K unlabeled images (ablation)Softargmax · 300W fullNMSE: 4.25 -> 4.29No clear effect
add adversarial training with 70K unlabeled images (ablation)LaplaceKL · 300W challengeNMSE: 7.01 -> 6.87Improved
use 300W itself as unlabeled set in adversarial branch (ablation)LaplaceKL · 300W fullNMSE: 4.01 -> 4.06No clear effect
use 300W itself as unlabeled set in adversarial branch (ablation)Softargmax · 300W fullNMSE: 4.24 -> 4.26No clear effect
reduce channels to 1/8 (0.0389M params) (ablation)Softargmax · 300W fullNMSE: 4.25 -> 6.86Hurt
reduce channels to 1/8 (0.0389M params) (ablation)LaplaceKL+D(70K) · 300W fullNMSE: 3.91 -> 4.85Hurt
reduce channels to 1/16 (0.0174M params) (ablation)LaplaceKL · 300W fullNMSE: 4.01 -> 7.38Hurt
LaplaceKL+D(70K) vs Softargmax+D(70K) at 1/16 channels (ablation)small RCN · 300W full (1/16 channels)NMSE: 9.02 -> 7.01Improved
add 70K unlabeled adversarial data to Softargmax at 1/16 channels (ablation)Softargmax · 300W full (1/16 channels)NMSE: 9.79 -> 9.02Improved

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