AI Paper Atlas

Research map / Image generation / Image restoration

Image Aesthetic Assessment Based on Pairwise Comparison A Unified Approach to Score Regression, Binary Classification, and Personalization

Jun-Tae Lee, Chang-Su Kim

ICCV 2019 · Image generation › Image restoration · approach: Image harmonization and color transformation · 47 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
use ternary instead of 5-ary quantization of score ratio (ablation)aesthetic comparator · AVA score regressionSpearman rho: 0.791 -> 0.918Improved
use ternary instead of 7-ary quantization of score ratio (ablation)aesthetic comparator · AVA score regressionSpearman rho: 0.779 -> 0.918Improved
use ternary instead of 5-ary quantization (ablation)aesthetic comparator · AADB score regressionMASD: 0.1713 -> 0.1141Improved
use ternary instead of 7-ary quantization (ablation)aesthetic comparator · AADB score regressionSpearman rho: 0.867 -> 0.879Improved
add pairwise comparison with reference images to baseline networkbaseline network · AVA binary classificationaccuracy (%): 78.7 -> 91.5Improved
use pairwise-comparison classifier instead of A-Lampproposed · AVA binary classificationaccuracy (%): 82.5 -> 91.5Improved
use proposed regressor instead of Reg-Netproposed · AVA score regressionMASD: 0.0582 -> 0.0229Improved
use proposed regressor instead of PAC-Netproposed · AVA score regressionSpearman rho: 0.871 -> 0.918Improved
add 10 personal reference images (ablation)proposed · FLICKER-AESSpearman rho: 0.668 -> +0.040Improved
add 100 personal reference images instead of 10 (ablation)proposed · FLICKER-AESSpearman rho: +0.040 -> +0.044Mixed

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