AI Paper Atlas

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

Deep Credible Metric Learning for Unsupervised Domain Adaptation Person Re-identification

Guangyi Chen, Yuhao Lu, Jiwen Lu, Jie Zhou

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 113 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 GAN-translated source images for pre-training (ablation)UDA (reproduced) · Market-1501 to DukeMTMC-reIDmAP: 54.4 -> 60.4Improved
add GAN-translated source images for pre-training (ablation)UDA (reproduced) · DukeMTMC-reID to Market-1501mAP: 56.5 -> 70.5Improved
add credible anchor mining and IMS loss to UDA (no GAN) (ablation)UDA (reproduced) · Market-1501 to DukeMTMC-reIDmAP: 54.4 -> 60.2Improved
add credible anchor mining and IMS loss to UDA (no GAN) (ablation)UDA (reproduced) · DukeMTMC-reID to Market-1501mAP: 56.5 -> 69.2Improved
add instance margin spreading loss (ablation)UDA + GAN · Market-1501 to DukeMTMC-reIDmAP: 60.4 -> 62.2Improved
add instance margin spreading loss (ablation)UDA + GAN · DukeMTMC-reID to Market-1501mAP: 70.5 -> 71.3Improved
add credible anchor mining strategy (KNN) (ablation)UDA + GAN + IMSLoss · Market-1501 to DukeMTMC-reIDmAP: 62.2 -> 63.3Improved
add credible anchor mining strategy (KNN) (ablation)UDA + GAN + IMSLoss · DukeMTMC-reID to Market-1501mAP: 71.3 -> 72.6Improved
use prototype similarity instead of KNN similarity for credibility (ablation)DCML · Market-1501 to DukeMTMC-reIDmAP: 63.3 -> 63.5No clear effect
use prototype similarity instead of KNN similarity for credibility (ablation)DCML · DukeMTMC-reID to Market-1501mAP: 72.6 -> 72.3No clear effect
use DCML instead of SSG++unsupervised domain adaptation re-ID · Market-1501 to DukeMTMC-reIDmAP: 60.3 -> 63.3Improved
use DCML instead of PASTunsupervised domain adaptation re-ID · CUHK03 to DukeMTMC-reIDmAP: 51.8 -> 56.9Improved

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