AI Paper Atlas

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

Label Distribution Learning Forests

Wei Shen, KAI ZHAO, Yilu Guo, Alan L. Yuille

NeurIPS 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 80 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
use sLDLF instead of the strongest listed baselinestand-alone LDL · MovieK-L: 0.086$\pm$0.004 -> 0.073$\pm$0.005Improved
use sLDLF instead of the strongest listed baselinestand-alone LDL · Human GeneK-L: 0.231$\pm$0.021 -> 0.228$\pm$0.006Improved
use sLDLF instead of the strongest listed baselinestand-alone LDL · Natural SceneK-L: 0.852$\pm$0.023 -> 0.534$\pm$0.013Improved
replace DLDL with dLDLFVGG-Face age estimation model · MorphMAE: 2.42$\pm$0.01 -> 2.24$\pm$0.02Improved
add more trees to the forest (ablation)LDLF · MovieK-L: K=20: K-L~=~0.071; K=100: K-L~=~0.070Improved
replace the LDLF ensemble strategy with the dNDFs ensemble strategy (ablation)LDLF · MovieK-LHurt
increase tree depth from 9 to 18 (ablation)LDLF · MovieK-L: h=18: K-L~=~0.1162 vs h=9: K-L~=~0.0831Hurt

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