AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Understanding Perceptual and Conceptual Fluency at a Large Scale

Shengli Hu, Ali Borji

ECCV 2018 · Probabilistic and scientific modeling › Causal discovery · approach: Causal representation identifiability · 1 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
fine-tune last three layers instead of transfer learning onlyResNet50 with ImageNet init · Logo design rank correlationrank correlation: 0.50 -> 0.58Improved
fine-tune last three layers instead of transfer learning onlyInceptionV3 with random init · Logo design rank correlationrank correlation: 0.50 -> 0.54Improved
use ImageNet instead of random weight initialization (ablation)ResNet50 fine-tuned · Logo design rank correlationrank correlation: 0.58 -> 0.58No clear effect
use ImageNet instead of random weight initialization (ablation)AlexNet transfer · Logo design rank correlationrank correlation: 0.37 -> 0.41Improved
use ImageNet instead of random weight initialization (ablation)VGG16 transfer · Logo design rank correlationrank correlation: 0.40 -> 0.38Hurt
replace AlexNet with ResNet50 backbonefine-tuned, ImageNet init · Logo design rank correlationrank correlation: 0.39 -> 0.58Improved
increase perceptual complexitylinear regression on memorability · Logo memorability regressioncoefficient: 0.290Improved
increase perceptual complexitylinear regression on likability · Logo likability regressioncoefficient: -0.027Hurt
increase conceptual entropy (more ambiguous)linear regression on memorability · Logo memorability regressioncoefficient: -0.018Hurt
increase conceptual KL divergencelinear regression on memorability · Logo memorability regressioncoefficient: 0.006Improved
add Perceptual Complexity squared termregression on memorability · Logo memorability regressioncoefficient: -0.074Hurt
interaction of PPI and conceptual entropyregression on likability · Logo likability regressioncoefficient: 0.006Improved

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