AI Paper Atlas

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

Faceptor: A Generalist Model for Face Perception

Lixiong Qin, Mei Wang, Xuannan Liu, Yuhang Zhang, Wei Deng, Xiaoshuai Song, Weiran Xu, Weihong Deng

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 18 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 per-category output heads (Naive Faceptor) with shared task-specific queries (Faceptor)Faceptor-Base · parametersparameters (M): 178.9 -> 103.2Improved
use task-specific queries instead of standardized headsFaceptor-Base · RAF-DBaccuracy: 87.58 -> 90.38Improved
use task-specific queries instead of standardized headsFaceptor-Base · Face recognition mean1:1 verification accuracy mean: 95.57 -> 95.10Hurt
add Layer-Attention trained with two-stage process (ablation)Faceptor-Base · RAF-DBaccuracy: 89.80 -> 90.38Improved
add Layer-Attention trained with two-stage process (ablation)Faceptor-Base · MORPH IIMAE: 1.882 -> 1.869Improved
add Layer-Attention directly without two-stage training (ablation)Faceptor-Base · MORPH IIMAE: 1.882 -> 1.970Hurt
add Layer-Attention to binary attribute classification (ablation)Faceptor-Base · CelebAmAcc: 91.40 -> 91.43No clear effect
add auxiliary tasks (landmark, parsing, recognition) to age estimation (ablation)Faceptor · MORPH IIMAE: 1.869 -> 1.787Improved
add auxiliary tasks to expression recognition (ablation)Faceptor · RAF-DBaccuracy: 90.38 -> 91.92Improved
joint training on 13 datasets from FaRL initialization versus specialized ViT trained from scratchFaceptor-Full · Face verification meanmean accuracy: 96.46 -> 95.28Hurt
tune only task-specific queries (prompt tuning) vs all parameters on novel semantics (ablation)Faceptor-Base · LFW-73 transfermAcc: 85.56 vs 87.95Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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