AI Paper Atlas

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

Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association

Dapeng Chen, Hongsheng Li, Xihui Liu, Yantao Shen, Jing Shao, Zejian Yuan, Xiaogang Wang

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 156 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 global discriminative association (GDA) (ablation)ResNet-50 baseline · Market-1501mAP: 74.4 -> 80.0Improved
add global discriminative association (GDA) (ablation)ResNet-50 baseline · CUHK-SYSUmAP: 85.8 -> 90.2Improved
add local reconstructive association (LRA) (ablation)ResNet-50 baseline · Market-1501mAP: 74.4 -> 79.6Improved
add local reconstructive association (LRA) (ablation)ResNet-50 baseline · CUHK-SYSUmAP: 85.8 -> 89.7Improved
add LRA to GDA (full method) (ablation)basel.+GDA · Market-1501mAP: 80.0 -> 81.8Improved
add GDA to LRA (full method) (ablation)basel.+LRA · Market-1501mAP: 79.6 -> 81.8Improved
use L_dis instead of ranking loss variant 2 (ablation)basel.+rank2 · Market-1501mAP: 77.7 -> 80.0Improved
use L_dis instead of ranking loss variant 2 (ablation)basel.+rank2 · CUHK-SYSUmAP: 88.8 -> 90.2Improved
use more positive pairs (any image-text of same person) in ranking loss (ablation)basel.+rank1 · Market-1501mAP: 75.5 -> 77.7Improved
add language ID loss L_T (lambda_T 0 -> 0.1) (ablation)basel.+GDA · Market-1501mAP: 78.9 -> 80.0Improved
add language ID loss L_T (lambda_T 0 -> 0.1) (ablation)basel.+GDA · CUHK-SYSUmAP: 89.3 -> 90.2Improved
raise lambda_T from 0.1 to 1 (ablation)basel.+GDA · Market-1501mAP: 80.0 -> 78.9Hurt

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