AI Paper Atlas

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

ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment

Yangyu Huang, Hao Yang, Chong Li, Jongyoo Kim, Fangyun Wei

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 78 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 ADL with lambda=2.0 (ablation)baseline · 300W fullset (no AAM)NME: 3.38 -> 3.23Improved
weight tangent direction more (lambda=0.5) instead of normal (ablation)ADL · 300W fullset (no AAM)NME: 3.38 -> 3.43Hurt
raise lambda from 2.0 to 8.0 (ablation)ADL · 300W fullset (no AAM)NME: 3.23 -> 3.27No clear effect
add AAM (anisotropic attention) (ablation)baseline · 300W fullset (no ADL)NME: 3.38 -> 2.98Improved
use AAM instead of point attention (ablation)attention module · 300W fullset (no ADL)NME: 3.12 -> 2.98Improved
use AAM instead of edge attention (ablation)attention module · 300W fullset (no ADL)NME: 3.09 -> 2.98Improved
add ADL and AAM (ablation)Stacked 4 HGNet · 300W fullsetNME: 3.38 -> 2.93Improved
add ADL and AAM (ablation)Single HGNet · 300W fullsetNME: 3.39 -> 2.99Improved
add ADL and AAM (ablation)ResNet50 · 300W fullsetNME: 3.43 -> 3.11Improved
add ADL and AAM (ablation)baseline · 300W normal-direction NMENME: 1.91 -> 1.54Improved
add ADL and AAM (ablation)baseline · 300W tangent-direction NMENME: 2.55 -> 2.28Improved
add ADL and AAM, raising error bias rate (ablation)baseline · 300W bias ratebias rate: 33.51% -> 48.05%Improved

Later papers that compared with this method

6 later accepted papers report ADNet as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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