AI Paper Atlas

Research map / Detection and segmentation / CNN features

RefineFace: Refinement Neural Network for High Performance Face Detection

Shifeng Zhang, Cheng Chi, Zhen Lei, Stan Ziqing Li

TPAMI 2020 · Detection and segmentation › CNN features · approach: Efficient DETR query design · 119 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 selective two-step regression (ablation)RetinaNet baseline · WIDER FACE valAP (Hard): 88.0 -> 88.8Improved
add selective two-step classification (ablation)RetinaNet baseline · WIDER FACE valAP (Hard): 88.0 -> 89.4Improved
add receptive field enhancement (ablation)RetinaNet baseline · WIDER FACE valAP (Hard): 88.0 -> 88.3Improved
add scale-aware margin loss (ablation)RetinaNet baseline · WIDER FACE valAP (Hard): 88.0 -> 89.1Improved
add feature supervision module (ablation)RetinaNet baseline · WIDER FACE valAP (Hard): 88.0 -> 88.7Improved
add RFE after STR and STC (ablation)RefineFace · WIDER FACE valAP (Hard): 90.1 -> 90.2Improved
combine all five modules versus baseline (ablation)RetinaNet baseline · WIDER FACE valAP (Hard): 88.0 -> 91.1Improved
apply two-step regression to pyramid level P2 (ablation)RetinaNet baseline · WIDER FACE valAP (Hard): 88.0 -> 87.5Hurt
apply two-step regression to high pyramid level P7 (ablation)RetinaNet baseline · WIDER FACE valAP (Hard): 88.0 -> 88.4Improved
apply two-step classification to high levels P5-P7 (ablation)RetinaNet baseline · WIDER FACE valAP (Hard): 88.0 -> 87.7No clear effect
add STC to reduce false positives (ablation)RetinaNet · WIDER FACE valfalse positives at 95% recall: 466,534 -> 103,586Improved
add STR at IoU threshold 0.8 (ablation)RetinaNet · WIDER FACE val HardAP at IoU 0.8: 28.5 -> 38.2Improved

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