Saved in:
Bibliographic Details
Main Authors: Ren, Simiao, Shen, Xingyu, Raj, Ankit, Dai, Albert, Caroline, Zhang, Xu, Yuan, Chen, Zexi, Wu, Siqi, Gong, Chen, Zhang, Yuxin
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.07815
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908827321892864
author Ren, Simiao
Shen, Xingyu
Raj, Ankit
Dai, Albert
Caroline
Zhang
Xu, Yuan
Chen, Zexi
Wu, Siqi
Gong, Chen
Zhang, Yuxin
author_facet Ren, Simiao
Shen, Xingyu
Raj, Ankit
Dai, Albert
Caroline
Zhang
Xu, Yuan
Chen, Zexi
Wu, Siqi
Gong, Chen
Zhang, Yuxin
contents Facial age estimation plays a critical role in content moderation, age verification, and deepfake detection. However, no prior benchmark has systematically compared modern vision-language models (VLMs) with specialized age estimation architectures. We present the first large-scale cross-paradigm benchmark, evaluating 34 models - 22 specialized architectures with publicly available pretrained weights and 12 general-purpose VLMs - across eight standard datasets (UTKFace, IMDB-WIKI, MORPH, AFAD, CACD, FG-NET, APPA-REAL, and AgeDB), totaling 1,100 test images per model. Our key finding is striking: zero-shot VLMs significantly outperform most specialized models, achieving an average mean absolute error (MAE) of 5.65 years compared to 9.88 years for non-LLM models. The best-performing VLM (Gemini 3 Flash Preview, MAE 4.32) surpasses the strongest non-LLM model (MiVOLO, MAE 5.10) by 15%. MiVOLO - unique in combining face and body features using Vision Transformers - is the only specialized model that remains competitive with VLMs. We further analyze age verification at the 18-year threshold and find that most non-LLM models exhibit false adult rates between 39% and 100% for minors, whereas VLMs reduce this to 16%-29%. Additionally, coarse age binning (8-9 classes) consistently increases MAE beyond 13 years. Stratified analysis across 14 age groups reveals that all models struggle most at extreme ages (under 5 and over 65). Overall, these findings challenge the assumption that task-specific architectures are necessary for high-performance age estimation and suggest that future work should focus on distilling VLM capabilities into efficient specialized models.
format Preprint
id arxiv_https___arxiv_org_abs_2602_07815
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Out of the box age estimation through facial imagery: A Comprehensive Benchmark of Vision-Language Models vs. out-of-the-box Traditional Architectures
Ren, Simiao
Shen, Xingyu
Raj, Ankit
Dai, Albert
Caroline
Zhang
Xu, Yuan
Chen, Zexi
Wu, Siqi
Gong, Chen
Zhang, Yuxin
Computer Vision and Pattern Recognition
Facial age estimation plays a critical role in content moderation, age verification, and deepfake detection. However, no prior benchmark has systematically compared modern vision-language models (VLMs) with specialized age estimation architectures. We present the first large-scale cross-paradigm benchmark, evaluating 34 models - 22 specialized architectures with publicly available pretrained weights and 12 general-purpose VLMs - across eight standard datasets (UTKFace, IMDB-WIKI, MORPH, AFAD, CACD, FG-NET, APPA-REAL, and AgeDB), totaling 1,100 test images per model. Our key finding is striking: zero-shot VLMs significantly outperform most specialized models, achieving an average mean absolute error (MAE) of 5.65 years compared to 9.88 years for non-LLM models. The best-performing VLM (Gemini 3 Flash Preview, MAE 4.32) surpasses the strongest non-LLM model (MiVOLO, MAE 5.10) by 15%. MiVOLO - unique in combining face and body features using Vision Transformers - is the only specialized model that remains competitive with VLMs. We further analyze age verification at the 18-year threshold and find that most non-LLM models exhibit false adult rates between 39% and 100% for minors, whereas VLMs reduce this to 16%-29%. Additionally, coarse age binning (8-9 classes) consistently increases MAE beyond 13 years. Stratified analysis across 14 age groups reveals that all models struggle most at extreme ages (under 5 and over 65). Overall, these findings challenge the assumption that task-specific architectures are necessary for high-performance age estimation and suggest that future work should focus on distilling VLM capabilities into efficient specialized models.
title Out of the box age estimation through facial imagery: A Comprehensive Benchmark of Vision-Language Models vs. out-of-the-box Traditional Architectures
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.07815