AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Image Cropping with Composition and Saliency Aware Aesthetic Score Map

Yi Tu, Li Niu, Weijie Zhao, Dawei Cheng, Liqing Zhang

AAAI 2020 · Image generation › Autoregressive and latent generation · approach: Classical generative image synthesis · 53 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 ASM-Net with composition- and saliency-aware score mapsVGG16-based image cropping model · FCDBIoU: 0.7349 -> 0.7489Improved
use ASM-Net with composition- and saliency-aware score mapsVGG16-based image cropping model · FLMSIoU: 0.8365 -> 0.8486Improved
use ASM-Net with composition- and saliency-aware score mapsVGG16-based image cropping model · GAICDSRCC: 0.735 -> 0.766Improved
add composition-aware partitioning instead of using one shared score per region (ablation)ASM-Net on CPC · CPC validationAccuracy: 59.46 -> 87.59Improved
use horizontal-aware 1×3 grid rather than vertical-aware 3×1 grid (ablation)ASM-Net on CPC · CPC validationAccuracy: 71.33 -> 75.64Improved
use cross-rectangle composition pattern rather than 5×5 grid (ablation)ASM-Net on CPC · CPC validationAccuracy: 86.38 -> 87.59Improved
use cross-rectangle rather than multi-rectangle composition pattern (ablation)ASM-Net on CPC · CPC validationAccuracy: 81.34 -> 87.59Improved
use cross-rectangle rather than multi-direction composition pattern (ablation)ASM-Net on CPC · CPC validationAccuracy: 83.22 -> 87.59Improved
add saliency-aware loss with λ=0.1 (ablation)ASM-Net on CPC · CPC validationAccuracy: 3.22%Improved
increase saliency-loss trade-off λ beyond 0.1 (ablation)ASM-Net on CPC · CPC validationAccuracyHurt

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