AI Paper Atlas

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

Fast Multi-Instance Multi-Label Learning

Sheng-Jun Huang, Wei Gao, Zhi‐Hua Zhou

TPAMI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 92 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 shared low-dimensional space W0 across labels (ablation)MIMLfast · Sceneaverage precision: .730 -> .770Improved
add shared low-dimensional space W0 across labels (ablation)MIMLfast · Reutersaverage precision: .963 -> .972Improved
add shared low-dimensional space W0 across labels (ablation)MIMLfast · Scenehamming loss: .211 -> .188Improved
add dummy label for choosing relevant labels instead of top-r (ablation)MIMLfast · Scenehamming loss: .196 -> .188Improved
add dummy label for choosing relevant labels instead of top-r (ablation)MIMLfast · Reutershamming loss: .035 -> .028Improved
add dummy label for choosing relevant labels instead of top-r (ablation)MIMLfast · Sceneaverage precision: .767 -> .770No clear effect
add dummy label for choosing relevant labels instead of top-r (ablation)MIMLfast · Reutersaverage precision: .971 -> .972No clear effect
use K=10 sub-concepts per label instead of K=1 (ablation)MIMLfast · Sceneaverage precision: .754 -> .777Improved
use K=10 sub-concepts per label instead of K=1 (ablation)MIMLfast · Sceneranking loss: .209 -> .184Improved
use K=10 sub-concepts per label instead of K=1 (ablation)MIMLfast · Reutersaverage precision: .972 -> .976Improved
increase K from 10 to 15 (ablation)MIMLfast · Sceneaverage precision: .777 -> .769No clear effect

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