AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Effective Aesthetics Prediction With Multi-Level Spatially Pooled Features

Vlad Hosu, Bastian Goldlucke, Dietmar Saupe

CVPR 2019 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 191 citations (OpenAlex)

Check 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 Pool-3FC with wide MLSP features instead of Single-3FC with narrow features (ablation)Inception-v3 features on AVA · AVA test set, original-resolution imagesSRCC: 0.729 -> 0.745Improved
Use Pool-3FC with wide MLSP features instead of Single-3FC with narrow features (ablation)InceptionResNet-v2 features on AVA · AVA test set, original-resolution imagesSRCC: 0.743 -> 0.756Improved
Add crop and flip augmentation (ablation)Single-3FC on AVA rescaled images · AVA test setSRCC: 0.668 -> 0.676Improved
Add crop and flip augmentation (ablation)Pool-3FC with InceptionResNet-v2 features · AVA test set, original-resolution imagesSRCC: 0.752 -> 0.756Improved
Use a 3FC head instead of a single fully connected layer (ablation)Inception-v3 narrow features on AVA · AVA test set, rescaled imagesSRCC: 0.644 -> 0.676Improved
Use all 11 feature blocks instead of only the last 5 (ablation)Single-1FC on Inception-v3 features · AVA test set, rescaled imagesSRCC: 0.570 -> 0.644Improved
Use separate 3FC heads for each feature block rather than one shared head (ablation)Inception-v3 narrow features on AVA · AVA test set, rescaled imagesSRCC: 0.676 -> 0.673No clear effect
Increase the Single-3FC dropout rates to (0.5, 0.5, 0.75) (ablation)Fine-tuned Inception-v3 head on AVA · AVA test set, rescaled imagesSRCC: 0.658 -> 0.675Improved
Train on original-resolution images rather than rescaled imagesProposed Pool-3FC method · AVA test setSRCC: 0.676 -> 0.756Improved
Use pre-trained feature learning instead of end-to-end fine-tuningSingle-3FC on Inception-v3 · AVA test set, rescaled imagesSRCC: 0.658 -> 0.676Improved
Use InceptionResNet-v2 rather than Inception-v3 for feature extractionPool-3FC on AVA original-resolution images · AVA test setSRCC: 0.745 -> 0.756Improved
Optimize and evaluate for SRCC rather than binary accuracyAesthetics assessment on AVA · AVA test setSRCC: 0.612 -> 0.756Improved

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