AI Paper Atlas

Research map / Detection and segmentation / CNN features

ProgressFace: Scale-Aware Progressive Learning for Face Detection

Jiashu Zhu, Dong Li, Tiantian Han, Lu Tian, Yi Shan

ECCV 2020 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 23 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 progressive large-to-small training (ablation)ProgressFace (MobileNet-0.25) · WIDER FACE val HardAP: 0.851 -> 0.858Improved
add progressive large-to-small training (ablation)ProgressFace (MobileNet-0.25) · WIDER FACE val EasyAP: 0.937 -> 0.945Improved
add KL-loss uncertainty estimation (ablation)ProgressFace (MobileNet-0.25) · WIDER FACE val HardAP: 85.8% -> 86.3%Improved
add anchor-free enhancement module (ablation)ProgressFace (MobileNet-0.25) · WIDER FACE val HardAP: 86.3% -> 87.9%Improved
train baseline for longer (ablation)ProgressFace (MobileNet-0.25) baseline · WIDER FACE val HardAP: 85.1% -> 85.3%No clear effect
use progressive training at equal epochs (ablation)ProgressFace (MobileNet-0.25) · WIDER FACE val HardAP: 85.3% -> 85.8%Improved
add anchor-free branch to anchor-based training (ablation)ProgressFace (MobileNet-0.25) · WIDER FACE val HardAP: 0.851 -> 0.860Improved
use anchor-free only instead of anchor-based only (ablation)ProgressFace (MobileNet-0.25) · WIDER FACE val HardAP: 0.851 -> 0.813Hurt
place anchor-free module on P3 rather than P5 (ablation)ProgressFace (MobileNet-0.25) · WIDER FACE val HardAP: 0.864 -> 0.879Improved
add anchor-free module to every anchor-based branch (ablation)ProgressFace (MobileNet-0.25) · WIDER FACE val HardAPNo clear effect
combine anchor-free outputs at test time (ablation)ProgressFace (MobileNet-0.25) · WIDER FACE val HardAP: 0.879 -> 0.876Hurt
use ProgressFace-Light instead of RetinaFace + DCNv2MobileNet-0.25 · WIDER FACE val HardAP: 79.5% -> 87.9%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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