AI Paper Atlas

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

Foreground-Aware Pyramid Reconstruction for Alignment-Free Occluded Person Re-Identification

Lingxiao He, Yinggang Wang, Wu Liu, He Zhao, Zhenan Sun, Jiashi Feng

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Cross-modality and occlusion re-identification · 191 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 foreground-aware pyramid reconstruction matchingBaseline ReID model · Occluded REIDRank-1: 42.12 -> 78.30Improved
add foreground-aware pyramid reconstruction matchingBaseline ReID model · Partial REIDRank-1: 53.33 -> 81.00Improved
add foreground-aware pyramid reconstruction matchingBaseline ReID model · Partial iLIDSRank-1: 52.94 -> 68.08Improved
add foreground-aware pyramid reconstruction matchingBaseline ReID model · Market1501Rank-1: 94.06 -> 95.42Improved
add foreground-aware pyramid reconstruction matchingBaseline ReID model · CUHK03Rank-1: 73.57 -> 76.08Improved
add foreground-aware pyramid reconstruction matchingBaseline ReID model · DukeMTMCRank-1: 87.30 -> 88.64Improved
use FPR instead of DSR reconstruction matchingDSR · Occluded REIDRank-1: 72.80 -> 78.30Improved
use FPR instead of DSR reconstruction matchingDSR · Partial REIDRank-1: 73.67 -> 81.00Improved
use FPR instead of DSR reconstruction matchingDSR · Market1501mAP: 85.78 -> 86.58Improved
use FPR instead of DSR reconstruction matchingDSR · DukeMTMCmAP: 77.07 -> 78.42Improved
set foreground loss weight alpha to 0.02 (swept 0.01 to 0.04) (ablation)FPR · Occluded datasets (Rank-1 and mAP)Rank-1 / mAPImproved
set foreground label threshold tau near 0.35 (swept 0 to 1) (ablation)FPR · Occluded datasets (Rank-1 and mAP)Rank-1 / mAPImproved

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