AI Paper Atlas

Research map / Image generation / GANs

Deep Convolutional Sum-Product Networks

Cory J. Butz, Jhonatan S. Oliveira, André E. dos Santos, André L. Teixeira

AAAI 2019 · Image generation › GANs · approach: GAN-based image manipulation · 20 citations (OpenAlex)

Read the paper

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 Gaussian low-pass smoothing post-processing (ablation)DCSPN · Olivetti Face left-completionMSE: 455 -> 401Improved
train with differentiable MPE objective instead of NLL (ablation)DCSPN · Olivetti Face left-completionMSE: 455 -> 651Hurt
use height-by-width filters instead of 1-by-1 filters (no parameter sharing) (ablation)DCSPN · image completionMSEImproved
use average-pooling, parameter sharing, batch norm, dropout (ablation)DCSPN · image completionMSENo clear effect
keep sum instead of max in convolutional layers during MPE (ablation)DCSPN · image completionMSEImproved
DCSPN vs DCGANDCGAN · Olivetti Face left-completionMSE: 935 -> 455Improved
DCSPN vs DCGANDCGAN · Caltech Face bottom-completionMSE: 1046 -> 1149Hurt
DCSPN vs DCGANDCGAN · Caltech Dolphin left-completionMSE: 4096 -> 2002Improved

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