AI Paper Atlas

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

Nonlinear Feature Extraction with Max-Margin Data Shifting

Jianqiao Wangni, Ning Chen

AAAI 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 3 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
apply MMDS before feature extraction (ablation)FA on RFF · MNISTaccuracy (%): 64.9 -> 74.4Improved
apply MMDS before feature extraction (ablation)FA on RFF · Digitsaccuracy (%): 70.0 -> 86.1Improved
apply MMDS before feature extraction (ablation)NMF on RFF · Digitsaccuracy (%): 28.4 -> 72.1Improved
apply MMDS before feature extraction (ablation)SPCA on RFF · MNISTaccuracy (%): 30.3 -> 48.8Improved
apply MMDS before feature extraction (ablation)KM on RFF · Letteraccuracy (%): 17.9 -> 46.3Improved
apply MMDS before feature extraction (ablation)ICA on RFF · Digitsaccuracy (%): 62.8 -> 81.6Improved
apply MMDS before PCA (ablation)PCA · Digits, K=5accuracy (%): 58.3 -> 79.4Improved
apply MMDS before PCA (ablation)PCA · Letters, K=5accuracy (%): 35.1 -> 51.1Improved
apply MMDS before PCA at larger dimension (ablation)PCA · MNIST, K=20accuracy (%): 81.5 -> 83.0Improved
apply MMDS before autoencoder (ablation)AE · MNIST, K=10accuracy (%): 58.1 -> 76.3Improved
add supervised shifting (MMDS) to PCA (ablation)PCA · Yale Baccuracy (%): 12.9 -> 33.3Improved
use MMDS-PCA instead of SEPCA (ablation)MMDS-PCA · 11 tumoraccuracy (%): 88.9 -> 73.3Hurt

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