AI Paper Atlas

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

Discriminative Feature Learning With Consistent Attention Regularization for Person Re-Identification

Sanping Zhou, Fei Wang, Zeyi Huang, Jinjun Wang

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 123 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 basic triplet loss to softmax loss (multi-task) (ablation)ResNet50 softmax · Market1501 single-queryTop-1: 87.5 -> 89.1Improved
replace basic triplet loss with improved triplet loss (ablation)ResNet50 + attention module + BT · Market1501 single-queryTop-1 / mAP: 3.1% in Top 1 and 4.1% in mAPImproved
add attention module (without consistent attention regularizer) (ablation)ResNet50 variants · Market1501 single-queryTop-1: 0.3%, 0.1%, 0.3%, 0.5% and 0.5% in Top 1No clear effect
add consistent attention regularizer to attention network (ablation)ResNet50 + AM + S + IT · Market1501 single-queryTop-1: 93.9 -> 96.1Improved
add consistent attention regularizer to attention network (ablation)ResNet50 + AM + S · Market1501 single-queryTop-1: 87.8 -> 89.3Improved
add consistent attention regularizer to attention network (ablation)ResNet50 + AM + S + IT · Market1501 single-querymAP: 79.5 -> 84.7Improved
add consistent attention regularizer to attention network (ablation)ResNet50 + AM + S + IT · CUHK03 detectedTop-1: 85.5 -> 93.2Improved
replace basic triplet loss with improved triplet loss in full model (ablation)full model · Market1501 single-queryTop-1: 92.1 -> 96.1Improved
replace symmetric triplet loss with improved triplet loss in full model (ablation)full model · Market1501 single-queryTop-1: 94.2 -> 96.1Improved
use a large sparsity weight in the regularizer (ablation)full model · Market1501 single-queryTop-1 / mAPHurt
vary alpha, beta and margin m (ablation)full model · Market1501 single-queryTop-1 / mAPNo clear effect
use full method instead of MGNMGN · Market1501 single-querymAP: 86.9 -> 84.7Hurt

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