AI Paper Atlas

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

Doing the Best We Can With What We Have: Multi-Label Balancing With Selective Learning for Attribute Prediction

Emily Hand, Carlos Castillo, Rama Chellappa

AAAI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 52 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 Selective Learning with train target distribution to AttCNN (ablation)AttCNN · CelebA testaverage accuracy: 90.97 -> 91.05Improved
Use test distribution as Selective Learning target instead of train (ablation)AttCNN · CelebA testaverage accuracy: 91.05 -> 91.07No clear effect
Use balanced target in Selective Learning (ablation)AttCNN · CelebA testaverage accuracy: 90.97 -> 85.05Hurt
Add Selective Learning with train target distribution (ablation)AttCNN · LFWAaverage accuracy: 71.21 -> 71.49Improved
Use balanced target Selective Learning (ablation)AttCNN · LFWAaverage accuracy: 71.21 -> 73.03Improved
Use balanced target Selective Learning (ablation)AttCNN · UMD-AEDaverage accuracy: Table 6: 66.85 -> 59.46 (Balanced); text: 4% over AttCNN, 11% over MOONMixed
Use P(a)=0.5 target in Selective Learning (ablation)AttCNN · UMD-AEDaverage accuracy: 66.85 -> 71.11Improved
Use train-distribution Selective Learning (ablation)AttCNN · UMD-AEDaverage accuracy: 66.85 -> 67.40Improved
Replace MOON per-sample reweighting with batch-level balancing (Selective Learning)attribute CNN · CelebA testaverage accuracy: MOON Balanced 86.33 vs AttCNN Balanced 85.05 on CelebA; 70.49 vs 73.03 on LFWAMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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