AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Self-Critical Attention Learning for Person Re-Identification

Guangyi Chen, Chunze Lin, Liangliang Ren, Jiwen Lu, Jie Zhou

ICCV 2019 · Architectures and efficiency › Attention and transformers · approach: Sparse and structured attention · 167 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 self-critical module to spatial attention (ablation)spatial attention ResNet-50 · Market-1501mAP: 87.6 -> 88.9Improved
add self-critical module to channel attention (ablation)channel attention ResNet-50 · Market-1501mAP: 88.1 -> 89.3Improved
add triplet loss (ablation)ResNet-50 CE baseline · Market-1501mAP: +1.9%Improved
add label smoothing regularization (ablation)ResNet-50 CE+triplet · Market-1501mAP: +1.4%Improved
add horizontal flip feature averaging at inference (ablation)ResNet-50 CE · Market-1501mAP: 82.1 -> 82.2Improved
add spatial attention (ablation)ResNet-50 CE+flip+triplet+LSR · Market-1501mAP: 85.5 -> 87.6Improved
add channel attention (ablation)ResNet-50 CE+flip+triplet+LSR · Market-1501mAP: 85.5 -> 88.1Improved
use SCAL (spatial) instead of baseline in cross-domain transfer (ablation)ResNet-50 baseline · Market-1501 to DukeMTMC-ReIDmAP: 13.1 -> 17Improved
use SCAL (channel) instead of baseline in cross-domain transfer (ablation)ResNet-50 baseline · DukeMTMC-ReID to Market-1501mAP: 18.8 -> 23.8Improved
replace SPGAN feature extractor with SCAL (channel) (ablation)SPGAN · Market-1501 to DukeMTMC-ReIDmAP: 22.3 -> 28.4Improved
choose spatial vs channel attentionSCAL · Market-1501, CUHK03 vs DukeMTMC-ReIDmAP: 89.3 vs 88.9 (Market-1501); 79.6 vs 79.1 (DukeMTMC-ReID)Mixed

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