ERNIE-Image-Aes: Robust Image Aesthetics Scoring with Balanced Category Generalization
[📄 Paper]
🌟 Highlights
ERNIE-Image-Aes is a 8B vision-language model for image aesthetic scoring, initialized from
ArtiMuse
and fine-tuned on a diverse, professionally annotated dataset. It substantially outperforms existing aesthetic predictors (LAION-AES, ArtiMuse, UniPercept) in generalization across diverse image categories.
Key advantages:
Balanced predictions across photography, anime, design, everyday snapshots, and film photography
No systematic bias toward specific image types (e.g., AI-generated content or black-and-white photos)
Swiss-tournament based pairwise annotation for high-quality training labels
Achieves
0.7445 SRCC
and
0.7598 PLCC
on ERIA-1K benchmark
Disproportionately high scores for AI-generated/anime content
ArtiMuse
Overscores black-and-white photography and casual everyday snapshots
UniPercept
Strong preference for monochrome images; overscores casual snapshots
ERNIE-Image-Aes addresses these failure modes through a purpose-built annotation pipeline with explicit category balance.
📊 Results on ERIA-1K Benchmark
Model
SRCC
PLCC
LAION AES
0.2944
0.3138
ArtiMuse
0.4277
0.4704
UniPercept
0.4533
0.4748
ERNIE-Image-Aes
0.7445
0.7598
Annotation Protocol:
Pairwise Swiss-system tournament for stable and reproducible rankings
Tier labels from 1 to 10
Annotators recruited from professional backgrounds (Central Academy of Fine Arts, Sichuan Fine Arts Institute, Communication University of China, etc.)
All annotators passed aesthetic calibration screening prior to participation
ERNIE-Image-Aes huggingface.co is an AI model on huggingface.co that provides ERNIE-Image-Aes's model effect (), which can be used instantly with this baidu ERNIE-Image-Aes model. huggingface.co supports a free trial of the ERNIE-Image-Aes model, and also provides paid use of the ERNIE-Image-Aes. Support call ERNIE-Image-Aes model through api, including Node.js, Python, http.
ERNIE-Image-Aes huggingface.co is an online trial and call api platform, which integrates ERNIE-Image-Aes's modeling effects, including api services, and provides a free online trial of ERNIE-Image-Aes, you can try ERNIE-Image-Aes online for free by clicking the link below.
baidu ERNIE-Image-Aes online free url in huggingface.co:
ERNIE-Image-Aes is an open source model from GitHub that offers a free installation service, and any user can find ERNIE-Image-Aes on GitHub to install. At the same time, huggingface.co provides the effect of ERNIE-Image-Aes install, users can directly use ERNIE-Image-Aes installed effect in huggingface.co for debugging and trial. It also supports api for free installation.