AI Paper Atlas

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

Instance-Guided Context Rendering for Cross-Domain Person Re-Identification

Yanbei Chen, Xiatian Zhu, Shaogang Gong

ICCV 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 207 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 dual condition on target instances (ablation)CR-GAN · Market1501 -> DukeMTMCreIDRank-1: 43.3 -> 52.2Improved
add dual condition on target instances (ablation)CR-GAN · DukeMTMCreID -> Market1501Rank-1: 55.5 -> 59.6Improved
add dual condition on target instances, with LMP (ablation)CR-GAN+LMP · Market1501 -> DukeMTMCreIDRank-1: 48.7 -> 56.0Improved
add dual condition on target instances, with LMP (ablation)CR-GAN+LMP · DukeMTMCreID -> Market1501Rank-1: 59.2 -> 64.5Improved
add dual condition on target instances (ablation)CR-GAN · Market->Duke image qualityLPIPS diversity: 0.196 -> 0.281Improved
add identity loss (ablation)CR-GAN · Market1501 -> DukeMTMCreIDRank-1: 31.9 -> 52.2Improved
add camera loss (ablation)CR-GAN · Market1501 -> DukeMTMCreIDRank-1: 48.8 -> 52.2Improved
add context loss (ablation)CR-GAN · Market1501 -> DukeMTMCreIDRank-1: 48.5 -> 52.2Improved
add context loss (ablation)CR-GAN · DukeMTMCreID -> Market1501Rank-1: 57.4 -> 59.6Improved
add camera loss (ablation)CR-GAN · DukeMTMCreID -> Market1501Rank-1: 53.6 -> 59.6Improved
add LMP pooling at test timeCR-GAN · Market1501 -> DukeMTMCreIDRank-1: 52.2 -> 56.0Improved
combine CR-GAN synthetic pretraining with TAUDLTAUDL · Market1501 -> DukeMTMCreIDRank-1: 61.7 -> 68.9Improved

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