AI Paper Atlas

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

Ranking Models in Unlabeled New Environments

Xiaoxiao Sun, Yunzhong Hou, Weijian Deng, Hongdong Li, Liang Zheng

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical alignment and hypothesis testing · 12 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
use searched proxy instead of source validation set as proxyproxy for model ranking · Model ranking, MSMT17 source -> DukeMTMC-reID targetSpearman rho: 0.320 -> 0.858Improved
use PersonX instead of source validation set as proxyproxy for model ranking · Model ranking, MSMT17 source -> DukeMTMC-reID targetSpearman rho: 0.320 -> 0.816Improved
add camera annotation to the proxy search (ablation)proxy search · Model ranking, MSMT17 source -> DukeMTMC-reID targetSpearman rho: 0.858 -> 0.882Improved
use searched proxy instead of engine-based synthesisproxy for model ranking · Model ranking, MSMT17 source -> DukeMTMC-reID targetSpearman rho: 0.756 -> 0.858Improved
combine FID and variance gap in sampling score (lambda 0.6) rather than either alone (ablation)proxy search · Model ranking, MSMT17 source -> DukeMTMC-reID targetSpearman rhoImproved
replace FID with MMD in sampling score (ablation)proxy search · Model ranking, MSMT17 source -> DukeMTMC-reID targetSpearman rho: -0.0056 Spearman rho and -0.0161 Kendall tauNo clear effect
apply SPGAN style transfer to proxy sets (ablation)proxy sets · Model ranking, MSMT17 source -> DukeMTMC-reID targetSpearman rhoMixed
use intermediate cluster number K=20 rather than too small or too large (ablation)proxy search · Model ranking, MSMT17 source -> DukeMTMC-reID targetSpearman rhoImproved
increase number of proxy IDs N (ablation)proxy search · Model ranking, MSMT17 source -> DukeMTMC-reID targetSpearman rhoNo clear effect
use searched proxy instead of random combination of datasetsproxy for model ranking · Model ranking, MSMT17 source -> DukeMTMC-reID targetSpearman rho: +0.133 of rho and +0.176 of tauImproved
train IDE on searched proxy instead of pseudo-label dataIDE re-ID model · DukeMTMC-reID test, IDE trained on different setsmAP: 50.4 -> 27.9Hurt

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