AI Paper Atlas

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

AFS: An Attention-Based Mechanism for Supervised Feature Selection

Ning Gui, Danni Ge, Ziyin Hu

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 86 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
Reuse a pretrained learning model and globally fine-tune AFS for 40 steps instead of training AFS for 3000 steps (ablation)AFS on MNIST · MNISTfeature weight generation time: 218s -> 25sImproved
Reuse a pretrained learning model and globally fine-tune for 40 steps rather than train AFS for 3000 steps (ablation)AFS on MNIST · MNIST, top 25 featuresaccuracy: 87.05 -> 82.09Hurt
Freeze the reused learning module and tune only the attention module for 40 steps (ablation)AFS on MNIST · MNIST, top 25 featuresaccuracy: 87.05 -> 76.59Hurt
Use global rather than local tuning of the reused learning module, at 40 steps (ablation)AFS-R on MNIST · MNIST, top 25 featuresaccuracy: 76.59 -> 82.09Improved
Use global rather than local tuning of the reused learning module, at 40 steps (ablation)AFS-R on MNIST · MNIST, top 35 featuresaccuracy: 85.21 -> 88.02Improved
Use global rather than local tuning of the reused learning module, at 40 steps (ablation)AFS-R on MNIST · MNIST, top 65 featuresaccuracy: 91.17 -> 94.50Improved
Use global rather than local tuning of the reused learning module, at 40 steps (ablation)AFS-R on MNIST · MNIST, top 95 featuresaccuracy: 95.40 -> 95.76Improved
Increase global fine-tuning from 10 to 40 steps (ablation)AFS-R-GlobalTune on MNIST · MNIST, top 25 featuresaccuracy: 63.68 -> 82.09Improved
Increase local fine-tuning from 10 to 40 steps (ablation)AFS-R-LocalTune on MNIST · MNIST, top 25 featuresaccuracy: 72.33 -> 76.59Improved
Initialize AFS with Fisher Score feature weights (ablation)AFS on Lung_discrete · Lung_discreteaverage accuracy: +1.09%Improved
Initialize AFS with ReliefF feature weights (ablation)AFS on Lung_discrete · Lung_discreteaverage accuracy: +1.73%Improved
Initialize AFS with ReliefF feature weights (ablation)AFS on Isolet · Isoletaverage accuracy: about 1.77%Improved

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