AI Paper Atlas

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

Population-Based Evolutionary Gaming for Unsupervised Person Re-identification

Yunpeng Zhai, Peixi Peng, Mengxi Jia, Shiyong Li, Wei‐Qiang Chen, Xuesong Gao, Yonghong Tian

IJCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 22 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
train eight models jointly with shared pseudo-labels instead of one model (ablation)single model baseline · Market-1501mAP: 69.6 -> 76.4Improved
add population mutual learning (ablation)Multi-model · Market-1501mAP: 76.4 -> 78.5Improved
add population mutual learning (ablation)Multi-model · DukeMTMC-reIDmAP: 63.4 -> 66.1Improved
add selection of 3 of 8 networks (ablation)Multi-model + PML · Market-1501mAP: 78.5 -> 79.2Improved
add reproduction and mutation (ablation)Multi-model + PML + Sel. · Market-1501mAP: 79.2 -> 84.3Improved
add reproduction and mutation (ablation)Multi-model + PML + Sel. · DukeMTMC-reIDmAP: 66.9 -> 71.9Improved
add multiple architectures on top of single-architecture PEG (ablation)Single architecture + PEG · Market-1501mAP: 80.1 -> 84.3Improved
add temporal average model to mutual learning (ablation)PML · Market-1501 (3 networks)mAP: 73.3 -> 79.2Improved
add mutual identity loss (ablation)PML · Market-1501 (3 networks)mAP: 77.2 -> 79.2Improved
add mutual triplet loss (ablation)PML · Market-1501 (3 networks)mAP: 77.0 -> 79.2Improved
use all models for pseudo-labels with ClusterContrast without selection (ablation)ClusterContrast · Market-1501mAP: 83.3 -> 79.4Hurt
add selection before multi-model CCL training (ablation)CCL-Multi · Market-1501mAP: 79.4 -> 84.3Improved

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