AI Paper Atlas

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

Efficient Facial Feature Learning with Wide Ensemble-Based Convolutional Neural Networks

Henrique Siqueira, Sven Magg, Stefan Wermter

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 155 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 shared representations and branch at level 3ESR-4 on CK+ · CK+accuracy: 85.5 ± 3.5 % -> 89.4 ± 2.2 %Improved
branch at level 4 instead of level 3 (ablation)ESR-4 on CK+ · CK+accuracy: 89.4 ± 2.2 % -> 88.5 ± 3.8 %Mixed
branch at level 4 instead of level 3 (ablation)ESR-4 on CK+ · CK+trainable parameters: $355.104$ -> $243.936$Improved
use a traditional ensemble rather than shared representationsfour-network ensemble on CK+ · CK+accuracy: 89.2 ± 1.2 % vs 89.4 ± 2.2 %No clear effect
train ensemble branches interleaved rather than sequentially (ablation)ESR on CK+ · CK+accuracyHurt
train new branches using shared layers as transferred feature knowledgeESR on CK+ · CK+training convergence: twice as accurate; around epoch 50Improved
collectively classify with nine branches instead of using a single branchESR-9 · AffectNet discrete emotionsaccuracy: 58.0\% -> 59.3\%Improved
train ESR-9 on balanced subsets capped at 5000 samples per emotion (ablation)ESR-9 · AffectNet discrete emotionsaccuracyImproved
fine-tune the AffectNet-trained ESR-9 on FER+ESR-9 · FER+accuracy: $57.92\%$ -> $87.153\%$Improved
lower the maximum training samples per emotion category (ablation)ESR-9 · FER+overall accuracyHurt
raise the maximum training samples per emotion category too high (ablation)ESR-9 · FER+ensemble diversityHurt
add arousal and valence output neurons while retaining the discrete-emotion networkESR-9 · AffectNet continuous affectRMSE: 0.33 and 0.36 RMSEImproved

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