AI Paper Atlas

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

Learning a Key-Value Memory Co-Attention Matching Network for Person Re-Identification

Yaqing Zhang, Xi Li, Zhongfei Zhang

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 6 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 2 heads instead of 1 (ablation)KVM-MN · CUHK03 labeled (1 split, ablation)rank-1: 85.3 -> 86.9Improved
use 4 heads instead of 1 (base) (ablation)KVM-MN · CUHK03 labeled (1 split, ablation)rank-1: 85.3 -> 87.1Improved
increase heads from 4 to 8 (ablation)KVM-MN · CUHK03 labeled (1 split, ablation)rank-1: 87.1 -> 86.2Hurt
replace key-value with K = V (ablation)KVM-MN · CUHK03 labeled (1 split, ablation)rank-1: 87.1 -> 83.5Hurt
increase feature dimension d from 256 to 1024 (ablation)KVM-MN · CUHK03 labeled (1 split, ablation)rank-1: 87.1 -> 88.3Improved
remove position embedding (ablation)KVM-MN · CUHK03 labeled (1 split, ablation)rank-1: 87.1 -> 86.8No clear effect
training gallery set M=2 random negatives instead of 10 (ablation)KVM-MN · CUHK03 labeled (1 split, ablation)rank-1: 87.1 -> 68.4Hurt
use hard negatives for M=2 instead of random (ablation)KVM-MN · CUHK03 labeled (1 split, ablation)rank-1: 68.4 -> 78.0Improved
increase gallery size M from 10 to 15 (ablation)KVM-MN · CUHK03 labeled (1 split, ablation)rank-1: 87.1 -> 88.0Improved
increase gallery size M from 15 to 30 (ablation)KVM-MN · CUHK03 labeled (1 split, ablation)rank-1: 88.0 -> 87.6No clear effect
pairwise metric learning instead of setwise matching network (ablation)KVM-MN · CUHK03 labeled (1 split, ablation)rank-1: 88.0 vs 85.4Hurt
add random erasing augmentation (ablation)KVM-MN · CUHK03 labeled (1 split, ablation)rank-1: 87.1 -> 88.2Improved

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