AI Paper Atlas

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

Multi-Task Learning With Coarse Priors for Robust Part-Aware Person Re-Identification

Changxing Ding, Kan Wang, Pengfei Wang, Dacheng Tao

TPAMI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 103 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 auxiliary tasks (naive MTL) to main-task-only model (ablation)MPN · Market-1501mAP: 85.6 -> 87.2Improved
add naive MTL over part-based baseline (ablation)Baseline · CUHK03-detectedRank-1: 70.9 -> 75.5Improved
add first 1x1 conv sharing (C1-S) between main and auxiliary tasks (ablation)Naive MTL · CUHK03-detectedRank-1: 75.5 -> 81.1Improved
add second 1x1 conv sharing (C2-S) (ablation)Naive MTL · CUHK03-detectedRank-1: 75.5 -> 80.6Improved
share both 1x1 conv layers rather than only the first (ablation)MTL with PSA · DukeMTMC-ReIDmAP: 80.7 -> 80.9Improved
add class-wise feature alignment (FSA) to naive MTL (ablation)Naive MTL · Market-1501mAP: 87.2 -> 88.3Improved
use class-wise instead of batch-wise alignment (ablation)FSA · DukeMTMC-ReIDmAP: 80.2 -> 80.7Improved
use class-wise instead of sample-wise alignment (with PSA) (ablation)FSA · Market-1501mAP: 88.6 -> 89.2Improved
use hard instead of soft parameter sharing (ablation)PSA · Market-1501 first 1x1 convRank-1/mAP: +0.4%/+0.3%Improved
use hard instead of soft parameter sharing (ablation)PSA · DukeMTMC-ReID first 1x1 convRank-1/mAP: +0.3%/+0.4%Improved
use coarse body-part prior instead of uniform division (ablation)MPN · Market-1501mAP: 88.8 -> 89.2Improved
use coarse body-part prior instead of ROI resize (ablation)MPN · DukeMTMC-ReIDmAP: 81.3 -> 81.6Improved

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