AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

DeepGUM: Learning Deep Robust Regression with a Gaussian-Uniform Mixture Model

Stephane Lathuiliere, Pablo Mesejo, Xavier Alameda-Pineda, Radu Horaud

ECCV 2018 · Learning theory and algorithms › Matrix and tensor methods · approach: High-dimensional estimation theory · 28 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
replace L2 loss with the Gaussian-uniform mixture (DeepGUM) lossVGG-16 regressor · FLD upper-bodyaverage MAE (pixels): 15.80 -> 15.63Improved
replace Biweight loss with DeepGUM lossVGG-16 regressor · FLD upper-bodyaverage MAE (pixels): 17.88 -> 15.63Improved
replace Huber loss with DeepGUM lossVGG-16 regressor · FLD upper-bodyaverage MAE (pixels): 18.08 -> 15.63Improved
use Biweight instead of L2 lossVGG-16 regressor · FLD upper-bodyaverage MAE (pixels): 15.80 -> 17.88Hurt
add DeepGUM loss (instead of L2)VGG-16 regressor · FLD lower-bodyaverage MAE (pixels): 8.87 -> 8.53Improved
add DeepGUM loss (instead of L2)VGG-16 regressor · FLD full-bodyaverage MAE (pixels): 11.89 -> 11.73Improved
add DeepGUM loss (instead of L2)VGG-16 regressor · McGill head pose (7-fold CV)MAE (degrees): 8.60 -> 7.61Improved
add DeepGUM loss (instead of Biweight)VGG-16 regressor · McGill head pose (7-fold CV)MAE (degrees): 7.81 -> 7.61Improved
add DeepGUM loss (instead of L2)VGG-16 regressor · CACD age estimationMAE (years): 5.08 years of MAE (0.7 years better than L2)Improved
add GUM mixture on top of Dex architecture (DexGUM)Dex · CACD age estimationMAE (years): p<0.001Improved
increase the share of uniformly generated outliers beyond 10% (l-UGO, g-UGO), DeepGUM vs L2/Biweight/Huber (ablation)DeepGUM · facial landmark detection (LFW+NET, synthetic outliers)failure rate: <10% comparable; larger amounts DeepGUM clearly superiorImproved
increase l-UGO outlier share to about 40% (ablation)DeepGUM · facial landmark detection (l-UGO)failure rate: breakdown point ~40%Hurt

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