AI Paper Atlas

Research map / Detection and segmentation / CNN features

Graininess-Aware Deep Feature Learning for Pedestrian Detection

Chunze Lin, Jiwen Lu, Gang Wang, Jie Zhou

ECCV 2018 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 166 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
use multi-layer detection instead of conv_fc7 only (ablation)GDFL backbone · Caltech Reasonablemiss rate: 16.86 -> 9.44Improved
use multi-layer detection instead of conv_fc7 only (ablation)GDFL backbone · Caltech Heavy Occlusionmiss rate: 53.44 -> 50.21Improved
add single-scale pedestrian attention (ablation)multi-layer backbone · Caltech Heavy Occlusionmiss rate: 50.21 -> 47.60Improved
use scale-aware attention instead of single-scale attention (ablation)GDFL · Caltech Heavy Occlusionmiss rate: 47.60 -> 44.68Improved
add instance-sensitive weight in attention loss (ablation)GDFL · Caltech Heavy Occlusionmiss rate: 47.69 -> 44.68Improved
add instance-sensitive weight in attention loss (ablation)GDFL · Caltech Reasonablemiss rate: 9.59 -> 8.44Improved
add ZIZOM on attention-encoded conv4_3 (ablation)GDFL · Caltech Heavy Occlusionmiss rate: 44.68 -> 43.18Improved
add ZIZOM on attention-encoded conv4_3 (ablation)GDFL · Caltech Mediummiss rate: 33.45 -> 32.50Improved
add ZIZOM on conv5_3 in addition to conv4_3 (ablation)GDFL · Caltechmiss rate: 43.18 -> 42.86 (Heavy), 7.36 -> 8.01 (Reasonable)No clear effect
add ZIZOM on conv4_3 without attention (ablation)multi-layer backbone · Caltech Heavy Occlusionmiss rate: 50.21 -> 45.73Improved
up-sample KITTI input by 1.5 times (384x1280 to 576x1920) (ablation)GDFL · KITTI HardmAP: 60.07 -> 66.86Improved

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