AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression

Xinyao Wang, Liefeng Bo, Li Fuxin

ICCV 2019 · Learning theory and algorithms › Prediction and decision losses · approach: Loss landscape analysis · 332 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 MSE loss with Adaptive Wing loss (ablation)MSE baseline · WFLW (GT-cropped)NME (%): 5.39 -> 4.65Improved
add Weighted Loss Map to AWing (ablation)AW · WFLW (GT-cropped)NME (%): 4.65 -> 4.30Improved
add Weighted Loss Map to MSE (ablation)MSE · WFLW (GT-cropped)NME (%): 5.39 -> 5.04Improved
use Weighted Loss Map instead of naive weight map (ablation)AW+WM · WFLW (GT-cropped)NME (%): 4.49 -> 4.30Improved
add boundary prediction (ablation)AW+WM · WFLW (GT-cropped)NME (%): 4.30 -> 4.28Improved
add CoordConv (ablation)AW+WM+B · WFLW (GT-cropped)NME (%): 4.28 -> 4.26Improved
add CoordConv with boundary coordinates (ablation)AW+WM+B+C · WFLW (GT-cropped)NME (%): 4.26 -> 4.21Improved
vary omega and epsilon in AWing (ablation)AWing · WFLW (GT-cropped)NME (%): 4.21 to 4.30No clear effect
vary theta from 0.3 to 0.7 (ablation)AWing · WFLW (GT-cropped)NME (%): 4.25, 4.22, 4.21, 4.26, 4.23No clear effect
increase hourglass stacks from 1 to 4 (ablation)AWing · WFLW (GT-cropped)NME (%): 4.50 -> 4.21Improved
train AWing on LSP instead of MSE (ablation)4HG · LSPPCK@0.2: 81.8 -> 85.9Improved
add label noise (30% points, 30% shift) to WFLW (ablation)AWing · WFLW (noisy labels)NME (%): 4.65 -> 4.86Hurt

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