AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Second-Order Non-Local Attention Networks for Person Re-Identification

Bryan (Ning) Xia, Yuan Gong, Yizhe Zhang, Christian Poellabauer

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 198 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 SONA after stage 2 (ablation)baseline with branches · CUHK03 labeled (new protocol)mAP: 77.05 -> 78.48Improved
add SONA after stage 2 (ablation)baseline with branches · Market1501mAP: 87.50 -> 88.50Improved
add SONA after stage 2 (ablation)baseline with branches · DukeMTMC-reIDmAP: 76.2 -> 78.18Improved
add DropBlock+ to baseline (ablation)baseline · CUHK03 labeled (new protocol)mAP: 77.05 -> 77.45No clear effect
add DropBlock+ to baseline (ablation)baseline · Market1501mAP: 87.50 -> 87.68No clear effect
add original DropBlock to baseline (ablation)baseline · CUHK03 labeled (new protocol)mAP: 77.05 -> 77.02No clear effect
add BFE batch erasing to baseline (ablation)baseline · CUHK03 labeled (new protocol)mAP: 77.05 -> 77.20No clear effect
place SONA after stage 4 instead of early stages (ablation)SONA-Net · CUHK03 labeled (new protocol)mAP: 75.8 -> 79.23Hurt
apply SONA after stage 2, stage 3 or both (ablation)SONA-Net · Market1501mAP: 88.67 vs 88.63 vs 88.83No clear effect
add SONA module overhead at inference (ablation)model with SONA2 · Market1501inference time (ms): 7.89 -> 8.44No clear effect
add DropBlock+ to baseline: training loss (ablation)baseline · CUHK03 labeled (new protocol)average training loss: +0.45%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