AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Deep Partial Multi-View Learning

Changqing Zhang, Yajie Cui, Zongbo Han, Joey Tianyi Zhou, Huazhu Fu, Qinghua Hu

TPAMI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware multi-view learning · 295 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
increase missing rate; compare CPM-Nets to LMNNCPM-Nets · CUBaccuracy: 89.48% vs 86.27%Improved
fill missing views with CRA instead of class averagescompared methods · multi-view datasets (eta=0.5)accuracyImproved
use CPM-Nets over second-best methodCPM-Nets · CUB, 3Sources-complete, Football, Politicsaccuracy: 2.5%, 10.2%, 36.7%, 6.6%Improved
use CPM-Nets on real partial dataCPM-Nets · ADNI and 3Sources-partialaccuracy: 3.4% and 2.3% higherImproved
add label supervision (lambda>0 vs lambda=0) (ablation)CPM-Nets · Handwritten (eta=0.5)accuracyImproved
vary trade-off lambda within 0.6-3 at K=128 (ablation)CPM-Nets · Handwritten (eta=0.5)accuracyNo clear effect
add fine-tuning to reduce train/test label gap (ablation)CPM-Nets · Handwritten and CUBaccuracyImproved
add adversarial strategy (CPM-GAN vs CPM-without-GAN) (ablation)CPM-Nets · six datasets, imputationNRMSEImproved
add adversarial strategy (ablation)CPM-Nets · Football or CUB, low missing rate, clusteringACC/NMIHurt
add adversarial strategy (ablation)CPM-Nets · clustering, high missing rateACC/NMIImproved
use CPM-GAN over second best at eta=0.5CPM-GAN · multi-modal datasets clusteringACC and NMI: 3.36% and 5.11%Improved
use CPM-GAN vs VIGAN (10% complete data for VIGAN)CPM-GAN · CUB and Animal clusteringACC and NMIImproved

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