AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Learning to Adapt Invariance in Memory for Person Re-identification

Zhun Zhong, Liang Zheng, Zhiming Luo, Shaozi Li, Yi Yang

TPAMI 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 200 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 exemplar-invariance learning (ablation)Source only model · Duke->Market-1501Rank-1: 43.1 -> 48.7Improved
add exemplar-invariance learning (ablation)Source only model · Market-1501->DukeRank-1: 28.9 -> 34.2Improved
add camera-invariance to EI model (ablation)Ours w/ EI · Duke->Market-1501Rank-1: 48.7 -> 63.1Improved
add neighborhood-invariance to EI model (ablation)Ours w/ EI · Market-1501->DukeRank-1: 34.2 -> 67.2Improved
add neighborhood-invariance to EI+CI (ablation)Ours w/ EI+CI · Duke->Market-1501Rank-1: 63.1 -> 84.1Improved
add camera-invariance to EI+NI (ablation)Ours w/ EI+NI · Duke->Market-1501Rank-1: 71.8 -> 84.1Improved
use exemplar memory instead of mini-batch invariance learning (ablation)Ours (VNS) · Duke->Market-1501Rank-1: 70.2 -> 77.4Improved
add graph-based positive prediction over vanilla neighbor selection (ablation)Ours with memory · Duke->Market-1501mAP: 45.5 -> 63.8Improved
threshold selection (p>=0.9) instead of top-8 with GPP (ablation)GPP · Duke->Market-1501Rank-1: 79.8 -> 84.1Improved
threshold selection on classifier without graph convolution (ablation)VNS · Duke->Market-1501Rank-1: 77.4 -> 77.0No clear effect
set temperature beta to 0.05 instead of 0.1 (ablation)Ours · Duke->Market-1501Rank-1: 75.7 -> 84.1Improved
set temperature beta to 0.05 instead of 0.01 (ablation)Ours · Duke->Market-1501Rank-1: 50.1 -> 84.1Improved

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