AI Paper Atlas

Research map / Image generation / GANs

Finding Tiny Faces in the Wild With Generative Adversarial Network

CVPR 2018 · Image generation › GANs · approach: GAN-based image manipulation · 228 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 the super-resolution and refinement GAN to the baseline detectorMB-FCN · WIDER FACE validation HardAP: 0.858 -> 0.873Helped
add the refinement network (ablation)Tiny Faces GAN · WIDER FACE validation HardAP: 0.863 -> 0.873Helped
add the refinement network (ablation)Tiny Faces GAN · WIDER FACE validation EasyAP: 0.940 -> 0.944Helped
add the refinement network (ablation)Tiny Faces GAN · WIDER FACE validation MediumAP: 0.929 -> 0.933Helped
add adversarial loss (ablation)Tiny Faces GAN · WIDER FACE validation EasyAP: 0.935 -> 0.944Helped
add adversarial loss (ablation)Tiny Faces GAN · WIDER FACE validation MediumAP: 0.925 -> 0.933Helped
add adversarial loss (ablation)Tiny Faces GAN · WIDER FACE validation HardAP: 0.867 -> 0.873Helped
add classification loss (ablation)Tiny Faces GAN · WIDER FACE validation EasyAP: 0.936 -> 0.944Helped
add classification loss (ablation)Tiny Faces GAN · WIDER FACE validation MediumAP: 0.927 -> 0.933Helped
add classification loss (ablation)Tiny Faces GAN · WIDER FACE validation HardAP: 0.865 -> 0.873Helped

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