AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Fine-grained Image Aesthetic Assessment: Learning Discriminative Scores from Relative Ranks

Zhichao Yang, Jianjie Wang, Zhixianhe Zhang, Pangu Xie, Xiangfei Sheng, Pengfei Chen, Leida Li

CVPR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Composed and text-based image retrieval · 2 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
add fine-grained ranking training to coarse-only training (ablation)FGAesQ · FGAestheticsSeries (s-Acc, s-SRCC)/2: 0.364 -> 0.600Improved
add coarse-grained pre-training to fine-only training (ablation)FGAesQ · FGAestheticsSeries (s-Acc, s-SRCC)/2: 0.299 -> 0.600Improved
use two-stage pretrain then joint alternating training instead of sequential Coarse | Fine (ablation)FGAesQ · FGAestheticsSeries (s-Acc, s-SRCC)/2: 0.380 -> 0.600Improved
add DiffToken (ablation)FGAesQ · FGAestheticsSeries (s-Acc, s-SRCC)/2: 0.423 -> 0.600Improved
add DiffToken (ablation)FGAesQ · FGAestheticsPair (Acc, F1)/2: 0.666 -> 0.753Improved
add CTAlign comparative text alignment (ablation)FGAesQ · FGAestheticsSeries (s-Acc, s-SRCC)/2: 0.581 -> 0.600Improved
add RankReg instead of direct ranking training (ablation)FGAesQ · FGAestheticsSeries (s-Acc, s-SRCC)/2: 0.571 -> 0.600Improved
add DiffToken at inference (w DiffToken vs w/o)FGAesQ · FGAesthetics Naturalseries s-SRCC: 0.664 -> 0.729Improved
fine-tune existing IAA model with ranking loss on FGAestheticsCharm · AVASRCC: 0.777 -> 0.470Hurt
fine-tune existing IAA model with ranking loss on FGAestheticsCharm · FGAestheticsSeries (s-Acc, s-SRCC)/2: 0.419 -> 0.477Improved
fine-tune NIMA with ranking lossNIMA · AVASRCC: 0.633 -> 0.330Hurt
use larger MLLM-based scorer instead of traditional deep modelQ-Align vs Charm · FGAesthetics Naturalseries s-SRCC: 0.404 -> 0.496Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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