AI Paper Atlas

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

Unsupervised Person Re-Identification with Wireless Positioning under Weak Scene Labeling

Yiheng Liu, Wengang Zhou, Qiaokang Xie, Houqiang Li

TPAMI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification

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 pseudo visual label training (second stage) (ablation)Initial Training · WP-ReIDmAP: 37.9 -> 54.7Improved
add MMGN with MGM and MMDA wireless similarity (ablation)Baseline · WP-ReIDmAP: 54.7 -> 66.3Improved
add MMGN with MGM and MMDA wireless similarity (ablation)Baseline · WP-ReIDRank-1: 85.6 -> 91.0Improved
add MMGN with MGM and MMDA wireless similarity (ablation)Baseline · Campus4KmAP: 80.8 -> 86.6Improved
use MGM histogram-based adjacency instead of plain averaged wireless similarity with GCN (ablation)BL + MMGN · WP-ReIDmAP: 60.0 -> 66.3Improved
use MGM adjacency instead of GAT-learned adjacency (ablation)BL + MMGN · WP-ReIDmAP: 61.3 -> 66.3Improved
use MGM adjacency instead of GAT-learned adjacency (ablation)BL + MMGN · Campus4KmAP: 84.6 -> 86.6Improved
train MMGN with cross-entropy only instead of adding triplet loss (ablation)MMGN · WP-ReIDmAP: 58.8 -> 66.3Improved
train MMGN with cross-entropy only instead of triplet loss (ablation)MMGN · Campus4KmAP: 83.4 -> 86.6Improved
replace baseline with CCUP contrastive baseline and add MMDA and MMGN (ablation)CCUP · Campus4KmAP: 88.3 -> 93.7Improved
replace baseline with CCUP contrastive baseline and add MMDA and MMGNCCUP · WP-ReIDmAP: 35.7 -> 72.2Improved
use CCUP baseline instead of original baseline in UMTFUMTF · WP-ReIDRank-1: 91.0 -> 84.6Hurt

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