AI Paper Atlas

Research map / Image generation / Super-resolution

FaceMoE: Mixture of Experts for Low-Resolution Face Recognition

Kartik Narayan, Vishal Patel

ECCV 2026 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 0 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 a single FFN with 3 FFN experts and a top-2 router plus auxiliary losses (ablation)Swin-B face encoder · TinyFaceRank-1: 75.10 -> 76.18Improved
add top-k router and MoE without auxiliary losses (ablation)FaceMoE · TinyFaceRank-1: 75.40 -> 74.94Hurt
add router z-loss and load balancing loss (ablation)FaceMoE · TinyFaceRank-1: 74.94 -> 76.18Improved
use learned routing instead of random expert assignment (ablation)FaceMoE · TinyFaceRank-1: 75.40 -> 76.18Improved
use full-capacity FFN experts instead of LoRA FFN experts (ablation)FaceMoE · TinyFaceRank-1: 43.61 -> 76.18Improved
use multiple experts instead of a single shared MLP expert (ablation)FaceMoE · TinyFaceRank-1: 62.71 -> 76.18Improved
increase number of experts from 3 to 8 (ablation)FaceMoE · TinyFaceRank-1: 76.18 -> 2.31Hurt
use N=3, k=2 instead of N=1 or N=4 (ablation)FaceMoE · BRIAR Protocol 3.1Rank-1: 70.2% (N=1) -> 73.1% (N=3, k=2)Improved
apply FaceMoE to a ViT-B backbone (ablation)ViT-B · BRIAR Protocol 3.1Rank-1: 55.59 -> 71.34Improved
apply FaceMoE to a ViT-B backbone (ablation)ViT-B · IJB-B TAR@FAR=1e-4TAR: 95.18 -> 89.75Hurt
scale pretraining data from WebFace4M to WebFace12M (ablation)FaceMoE · BRIAR Protocol 3.1Rank-1: 73.06 -> 74.77Improved
fine-tune CosFace on BRIAR instead of using the pretrained modelCosFace · BRIAR Protocol 3.1TAR@FAR=0.01%: 34.29 -> 11.62 (ViT-B pretrained vs finetuned)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