AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

NashAE: Disentangling Representations through Adversarial Covariance Minimization

Eric Yeats, Frank Liu, David Womble, Hai Li

ECCV 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Disentangled and discrete latent models · 4 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
add adversarial covariance loss (lambda 0 -> 0.2) (ablation)NashAE · CelebATAD: 0.235 -> 0.543Improved
raise lambda from 0.2 to 0.8 (ablation)NashAE · CelebATAD: 0.543 -> 0.474Hurt
add adversarial covariance loss (lambda 0 -> 0.002) (ablation)NashAE · dSpritesbeta-VAE metric (%): 91.41% -> 96.57%Improved
add adversarial covariance loss (lambda 0 -> 0.2) (ablation)NashAE · Beamsynthesis m=32abs. latent-count error: 28.75 -> 1Improved
add adversarial covariance loss (lambda 0 -> 0.3) (ablation)NashAE · Beamsynthesis m=8abs. latent-count error: 5.75 -> 0Improved
raise lambda from 0.2 to 0.3 at m=32 (ablation)NashAE · Beamsynthesis m=32abs. latent-count error: 1 -> 0.5Improved
raise lambda from 0 to 0.2 (ablation)NashAE · CelebA latent fixed pointaverage R^2 of latent predictions: 0.52 -> 0.04Improved
raise lambda from 0 to 0.2 (ablation)NashAE · CelebA latent fixed pointnumber of learned latents: 32 -> 22Improved
raise beta from 1 to 100 (ablation)β-VAE · CelebATAD: 0.158 -> 0.351Improved
raise beta from 100 to 250 (ablation)β-VAE · CelebATAD: 0.351 -> 0.307Hurt
raise beta from 1 to 8 on dSprites (ablation)β-VAE · dSpritesbeta-VAE metric (%): 84.63% -> 96.21%Improved
raise beta from 2 to 4 (ablation)β-TCVAE · dSpritesbeta-VAE metric (%): 95.01% -> 93.95%Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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