AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Image Aesthetic Assessment Assisted by Attributes through Adversarial Learning

Bowen Pan, Shangfei Wang, Qisheng Jiang

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 50 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 attributes as auxiliary multi-task targets (ablation)ResNet-50 rating network · AADB testSpearman rho: 0.6833 -> 0.6927Improved
add attributes as auxiliary multi-task targets (ablation)ResNet-50 rating network · AVA testSpearman rho: 0.6062 -> 0.6187Improved
add adversarial discriminator on joint score-attribute labels (ablation)multi-task network · AADB testSpearman rho: 0.6927 -> 0.7041Improved
add adversarial discriminator on joint score-attribute labels (ablation)multi-task network · AVA testSpearman rho: 0.6187 -> 0.6313Improved
add adversarial discriminatormulti-task network · AADB testmean abs difference of correlation matrix: 0.280 -> 0.250Improved
increase adversarial weight C beyond optimum (ablation)Ours · AADB testSpearman rhoHurt

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