AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Photo Aesthetics Ranking Network with Attributes and Content Adaptation

Shu Kong, Xiaohui Shen, Zhe Lin, Radomir Mech, Charless Fowlkes

ECCV 2016 · Image generation › Autoregressive and latent generation · approach: Learning-based image quality assessment · 532 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 pairwise ranking loss to regression (ablation)Reg · AADB testSpearman rho: 0.6239 -> 0.6515Improved
add pairwise ranking loss to regression (ablation)Reg · AVA testSpearman rho: 0.4995 -> 0.5126Improved
add ranking loss to attribute-adapted model (ablation)Reg+Att · AVA testSpearman rho: 0.5331 -> 0.5445Improved
add ranking loss (ablation)Reg · AVA testaccuracy (%): 72.04 -> 71.50No clear effect
sample pairs within-rater instead of cross-rater (ablation)Reg+Rank · AADB testSpearman rho: 0.6308 -> 0.6450Improved
combine within- and cross-rater sampling (ablation)Reg+Rank · AADB testSpearman rho: 0.6450 -> 0.6515Improved
sample 5 million instead of 2 million cross-rater pairs (ablation)Reg+Rank · AADB testSpearman rho: 0.6346 -> 0.6286No clear effect
sample 5 million instead of 2 million within-rater pairs (ablation)Reg+Rank · AADB testSpearman rho: 0.6450 -> 0.6448No clear effect
add attribute branch (ablation)Reg+Rank · AVA testSpearman rho: 0.5126 -> 0.5445Improved
add content-adaptive branches (ablation)Reg+Rank · AVA testSpearman rho: 0.5126 -> 0.5412Improved
add content-adaptive branches (ablation)Reg+Rank · AADB testSpearman rho: 0.6515 -> 0.6737Improved
add both attribute and content branches (ablation)Reg+Rank · AVA testaccuracy (%): 71.50 -> 77.33Improved

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