AI Paper Atlas

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

Deep Differentiable Random Forests for Age Estimation

Wei Shen, Yilu Guo, Yan Wang, Kai Zhao, Bo Wang, Alan Yuille

TPAMI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 96 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 DRF's regression forest instead of a classification forest (DNDF) (ablation)DRF · MORPH Setup IMAE: 3.32 -> 2.91Improved
add the forest structure instead of l2 regression loss (ablation)DRF · MORPH Setup IMAE: 3.21 -> 2.91Improved
use DRF leaf update functions instead of NRF's (ablation)DRF · MORPH Setup IMAE: 3.51 -> 2.91Improved
add DA for split nodes (ablation)DLDLF · MORPH Setup IMAE: 3.02 -> 2.94Improved
add DA for split nodes (ablation)DRF (full) · MORPH Setup IMAE: 2.85 -> 2.80Improved
add DA for split nodes (ablation)DRF (tau=1, kmeans) · MORPH Setup IMAE: 2.91 -> 2.85Improved
add kmeans initialization of leaf nodes (without leaf DA) (ablation)DRF (T=0, tau=1) · MORPH Setup IMAE: 6.91 -> 2.91Improved
add DA for leaf nodes (tau<1) without kmeans init (ablation)DRF · MORPH Setup IMAE: 2.85 -> 2.80Improved
add DA for leaf nodes (tau<1) without kmeans init, no split DA (ablation)DRF (T=0, tau=1) · MORPH Setup IMAE: 6.91 -> 2.85Improved
DRF vs DLDLF in MAE on MORPH Setup IIDRF vs DLDLF · MORPH Setup IIMAE: 2.19 -> 2.14Improved
DLDLF vs DRF in CS on MORPH Setup IIDLDLF vs DRF · MORPH Setup IICS: 91.3% -> 93.0%Mixed
train on small CACD val set: DRF vs DEXDRF · CACD test, trained on valMAE: 6.521 -> 5.630Improved

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