AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

Semi-attention Partition for Occluded Person Re-identification

Mengxi Jia, Yifan Sun, Yunpeng Zhai, Xinhua Cheng, Yi Yang, Ying Li

AAAI 2023 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 44 citations (OpenAlex)

This paper tried a common change: Add dropout

add supervision semantic dropout · Occluded-Duke · mAP: 61.8 -> 62.2 Improved

What 795 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 patch-to-patch semi-attention (ablation)Baseline re-ID model · Occluded-DukemAP: 56.0 -> 59.6Improved
add proxy-to-patch semi-attention (ablation)Baseline re-ID model · Occluded-DukemAP: 56.0 -> 60.1Improved
add both patch-to-patch and proxy-to-patch semi-attention (ablation)Baseline re-ID model · Occluded-DukemAP: 56.0 -> 62.2Improved
add mutual absorbing partition refinement (ablation)SAP · Occluded-DukemAP: 60.8 -> 62.2Improved
add supervision semantic dropout (ablation)SAP · Occluded-DukemAP: 61.8 -> 62.2Improved
use Pascal rather than ATR or lip for human-parsing teacher pretraining (ablation)SAP · Occluded-DukemAP: 61.4, 61.6 -> 62.2Improved
use a noisy semantic-partition teacher with SAP distillation (ablation)Transformer re-ID student · Occluded-DukemAP: 56.0 -> 62.2Improved
use SAP rather than PFDOccluded-REID · Occluded-REIDmAP: 83.0 -> 76.8Hurt
use SAP rather than FEDOccluded-REID · Occluded-REIDRank-1: 86.3 -> 83.0Hurt
use SAP rather than PFDMarket-1501 · Market-1501mAP: 89.7 -> 90.5Improved
use SAP rather than lipMarket-1501 · Market-1501Rank-1: 95.7 -> 96.0Improved
use SAP rather than TransReIDMSMT17 · MSMT17mAP: 67.4 -> 67.8Improved

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