AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

How Does Loss Function Affect Generalization Performance of Deep Learning? Application to Human Age Estimation

Ali Akbari, Muhammad Awais, Manijeh Bashar, Josef Kittler

ICML 2021 · Optimization › Implicit bias and generalization · approach: Stability-based generalization analysis · 14 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 KL divergence with GJM loss in LDLVGG age estimation, trained on BAG · avg over 5 test setsMAE: 4.75 -> 4.30Improved
replace KL divergence with GJM loss in LDLVGG age estimation, trained on SubBAG · avg over 5 test setsMAE: 5.55 -> 5.08Improved
replace KL divergence with GJM loss in LDLVGG age estimation, trained on MORPH · avg over 5 test setsMAE: 7.24 -> 7.12Improved
replace KL divergence with GJM loss in LDLResNet50 age estimation, trained on SubBAG · avg over 5 test setsMAE: 6.85 -> 5.90Improved
replace KL divergence with GJM lossVGG age estimation · generalization error, avg over test setsgeneralization error: 0.7038 -> 0.2037Improved
use label distribution learning (KL) instead of classificationVGG age estimation, trained on BAG · avg over 5 test setsMAE: 5.10 -> 4.75Improved
vary GJM alpha from 0.5 to 0.2 (ablation)GJM loss, VGG · FG-NETMAE: 3.2 -> 3.7Hurt
vary GJM alpha from 0.5 to 0.8 (ablation)GJM loss, VGG · FG-NETMAE: 3.2 -> 4.8Hurt
vary GJM alpha from 0.5 to 0.4 (ablation)GJM loss, VGG · FG-NETMAE: 3.2 -> 3.2No 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