AI Paper Atlas

Research map / Image generation / GANs

Enabling Dark Energy Science with Deep Generative Models of Galaxy Images

Siamak Ravanbakhsh, Francois Lanusse, Rachel Mandelbaum, Jeff Schneider, Barnabas Poczos

AAAI 2017 · Image generation › GANs · approach: GAN latent optimization and evaluation · 59 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 a conditional VAE to generate galaxy images conditioned on size, magnitude, and redshiftCOSMOS galaxy images · COSMOS validation setsizeImproved
Use a conditional VAE to generate galaxy images conditioned on size, magnitude, and redshiftCOSMOS galaxy images · COSMOS validation setbrightnessImproved
Use a conditional VAE to generate galaxy images conditioned on size, magnitude, and redshiftCOSMOS galaxy images · COSMOS validation setellipticity distributionMixed
Add a cross-correlation penalty to decorrelate latent codes from conditions (ablation)C-VAE · COSMOSnegative log-likelihoodHurt
Use a condition-independent prior without a cross-correlation penalty (ablation)C-VAE · COSMOSnegative log-likelihoodHurt
Use a condition-dependent prior p(z|y) instead of a condition-independent prior p(z) (ablation)C-VAE · COSMOSnegative log-likelihoodImproved
Use a conventional conditional GAN objective with continuous conditional variablesConditional GAN · COSMOStrainabilityHurt
Use the proposed predictor-based adversarial objectiveConditional GAN · COSMOScondition prediction errorImproved
Remove the min(0, .) operation from the predictor loss (ablation)Predictor-based conditional GAN · COSMOScondition prediction errorHurt
Use mini-batch discrimination to discourage generator collapsePredictor-based conditional GAN · Galaxy Zoomode collapseImproved
Add calibrated observational noise to generated C-VAE imagesC-VAE · COSMOS validation setimage-statistics comparabilityImproved
Generate images with the conditional GAN instead of the conditional VAEConditional generative models · COSMOS validation setconsistency of generated resultsHurt

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