CABRIA: contrastive attribute preference bridge for personalized image aesthetic assessment

Personalized Image Aesthetic Assessment (PIAA) aims to predict an individual user’s aesthetic ratings from a small set of images scored by that user. Generic aesthetic predictors are able to provide useful population-level knowledge, but they collapse the user-specific deviations that define personal taste. Direct few-shot adaptation can also entangle shared image quality with sparse user evidence, making it difficult to identify what should be personalized. To address this problem, we introduce CABRIA , a support-residual-conditioned framework that casts personalization as a user-specific correction over a global aesthetic prior. CABRIA first learns the generic prior and contrastively pretrains the representation used for support retrieval, then converts support-rating residuals into positive and negative preference memory. A Cross-Attention Bridge provides a structured route that connects positive and negative support evidence with query attribute tokens, and per-user gradient adaptation estimates the final residual correction. Under the 37-user FLICKR-AES protocol, CABRIA with ResNet-101 achieves SROCC scores of 0.694 and 0.760 for 10-shot and 100-shot personalization, respectively. A strict user-disjoint control that excludes validation- and test-user ratings from Stage 1 shows a statistically significant 10-shot improvement over the frozen prior and all matched adaptation baselines, while the multiplicity-corrected 100-shot comparisons do not establish an advantage for the complete pipeline. The code is available at CABRIA’s GitHub repository .

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-19
DOI
https://doi.org/10.1038/s41598-026-79826-y
Primary Topic
Image and Video Quality Assessment
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

CABRIA: contrastive attribute preference bridge for personalized image aesthetic assessment

Adnan Mahmood, Ziyuan Tao, Chuanzhi Xu
Scientific Reports
Image and Video Quality Assessment
article

CABRIA: contrastive attribute preference bridge for personalized image aesthetic assessment

Adnan Mahmood, Ziyuan Tao, Chuanzhi Xu
article en

Abstract

Personalized Image Aesthetic Assessment (PIAA) aims to predict an individual user’s aesthetic ratings from a small set of images scored by that user. Generic aesthetic predictors are able to provide useful population-level knowledge, but they collapse the user-specific deviations that define personal taste. Direct few-shot adaptation can also entangle shared image quality with sparse user evidence, making it difficult to identify what should be personalized. To address this problem, we introduce CABRIA , a support-residual-conditioned framework that casts personalization as a user-specific correction over a global aesthetic prior. CABRIA first learns the generic prior and contrastively pretrains the representation used for support retrieval, then converts support-rating residuals into positive and negative preference memory. A Cross-Attention Bridge provides a structured route that connects positive and negative support evidence with query attribute tokens, and per-user gradient adaptation estimates the final residual correction. Under the 37-user FLICKR-AES protocol, CABRIA with ResNet-101 achieves SROCC scores of 0.694 and 0.760 for 10-shot and 100-shot personalization, respectively. A strict user-disjoint control that excludes validation- and test-user ratings from Stage 1 shows a statistically significant 10-shot improvement over the frozen prior and all matched adaptation baselines, while the multiplicity-corrected 100-shot comparisons do not establish an advantage for the complete pipeline. The code is available at CABRIA’s GitHub repository .

Scientific Reports
The University of Sydney (AU), Macquarie University (AU)
Macquarie University
Image and Video Quality Assessment
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon