AI Paper Atlas

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

Occlude Them All: Occlusion-Aware Attention Network for Occluded Person Re-ID

Peixian Chen, Wenfeng Liu, Pingyang Dai, Jianzhuang Liu, Qixiang Ye, Mingliang Xu, Qi’an Chen, Rongrong Ji

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 173 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 occlusion augmentation (ablation)OAMN baseline (Lide+Ltri) · Occluded-DukeRank-1: 36.9 -> 51.2Improved
add grouped triplet loss Ltri-g (ablation)OAMN with OA · Occluded-DukeRank-1: 51.2 -> 55.5Improved
add attention-guided mask loss Lmask (ablation)OAMN with OA + Ltri-g · Occluded-DukeRank-1: 55.5 -> 57.7Improved
add occlusion unification at test time (ablation)OAMN with OA + Ltri-g · Occluded-DukeRank-1: 55.5 -> 60.3Improved
add both Lmask and OU (ablation)OAMN with OA + Ltri-g · Occluded-DukeRank-1: 55.5 -> 62.6Improved
use grouped triplet loss instead of vanilla triplet loss (ablation)OAMN · Occluded-DukeRank-1: 55.2 -> 62.6Improved
use grouped triplet loss instead of vanilla triplet loss (ablation)OAMN · Partial-REIDRank-1: 76.7 -> 86.0Improved
augment occlusion at all four locations instead of top/bottom only (ablation)OAMN · Occluded-DukeRank-1: 56.5 -> 62.6Improved
augment both 1/2 and 1/4 occlusion areas instead of 1/4 only (ablation)OAMN · Occluded-DukeRank-1: 52.8 -> 62.6Improved
attach mask module at layer-3 instead of layer-1 (ablation)OAMN · Occluded-DukeRank-1: 57.5 -> 62.6Improved
attach mask module at layer-3 instead of layer-4 (ablation)OAMN · Partial-REIDRank-1: 76.3 -> 86.0Improved
apply OAMN on top of its baseline for holistic ReIDOAMN · Market-1501Rank-1: 85.7 -> 93.2Improved

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