AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Counterfactual Generative Networks

Axel Sauer, Andreas Geiger

ICLR 2021 · Image generation › Autoregressive and latent generation · approach: Classical generative image synthesis · 36 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
Train classifiers on counterfactual images and predict the shape mechanism's labelMNIST classifiers · MNIST variants with shape-only test signalout-of-domain accuracyImproved
Add more counterfactual training examples while keeping real data fixed (ablation)MNIST classifiers · MNIST test domainstest accuracyImproved
Generate several counterfactuals per sampled noise vector (ablation)MNIST classifiers · MNIST test domainstest accuracyImproved
Use an even ratio of real and counterfactual images (ablation)ImageNet classifier · ImageNetclassification performanceImproved
Increase the counterfactual-to-real image ratio above 1 (ablation)ImageNet classifier · ImageNetclassification performanceNo clear effect
Use a counterfactual-to-real image ratio below 1 (ablation)ImageNet classifier · ImageNetclassification performanceHurt
Remove the shape loss (ablation)ImageNet CGN · ImageNet composite-image generationInception Score and mask qualityHurt
Add the shape loss, including binary-mask and mask-size constraints (ablation)ImageNet CGN · ImageNet composite-image generationInception Score and mask qualityImproved
Remove the texture loss (ablation)ImageNet CGN · ImageNet mechanism disentanglementmechanism disentanglementHurt
Add the texture loss (ablation)ImageNet CGN · ImageNet mechanism disentanglementmechanism disentanglementImproved
Remove the background loss (ablation)ImageNet CGN · ImageNet mechanism disentanglementmechanism disentanglementHurt
Add the background loss (ablation)ImageNet CGN · ImageNet mechanism disentanglementmechanism disentanglementImproved

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