AI Paper Atlas

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

Safe Classification with Augmented Features

Chenping Hou, Ling‐Li Zeng, Dewen Hu

TPAMI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 42 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 the second view of features to a multi-view method (MLRR)MLRR · AD1add2accuracy: 0.8381 -> 0.7652Hurt
add the second view of features to a multi-view method (MLRR)MLRR · AD1add3accuracy: 0.8381 -> 0.7234Hurt
add the second view of features to MvFDAMvFDA · AD1add2accuracy: 0.8658 -> 0.8349Hurt
add the second view of features to McMKLMcMKL · AD1add2accuracy: 0.9015 -> 0.9597Improved
use SEC with augmented features instead of the best single-view classifierSEC · Ionoshpere (30% train)accuracy: .9094 -> .9418Improved
use SEC instead of best single-view classifierSEC · MSRC-v1-1add4 (30% train)accuracy: .6755 -> .7772Improved
use SEC instead of best single-view classifierSEC · SensIT (30% train)accuracy: .5017 -> .8132Improved
adapt Naive Bayes with augmented features (AdNaiveBayes) (ablation)Naive Bayes · MSRC-v1-1add4 (30% train)accuracy: .6755 -> .4136Hurt
adapt Boosting with augmented features (AdBoosting) (ablation)Boosting · Digit1add2 (30% train)accuracy: .8021 -> .6550Hurt
use SEC integration of all adapted classifiers instead of single AdSVM(RBF) (ablation)AdSVM(RBF) · Ionoshpere (30% train)accuracy: .8721 -> .9418Hurt
integrate adapted classifiers (SEC) versus best single-viewSEC · 16 data sets, accuracyaccuracy: 32/0/0Improved
adapt Naive Bayes classifier with augmented features (ablation)AdNaiveBayes · 16 data sets, accuracyaccuracy: 18/4/10Mixed

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