AI Paper Atlas

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

Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders

Ananya Harsh Jha, Saket Anand, Maneesh Singh, VSR Veeravasarapu

ECCV 2018 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Disentangled and discrete latent models · 116 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 reverse cycle-consistency VAE instead of Mathieu et al.specified/unspecified disentangling · MNIST (z dim 16, s dim 16)z-space test accuracy (lower is better): 66.83 -> 17.56Improved
use reverse cycle-consistency VAE instead of Mathieu et al.specified/unspecified disentangling · MNIST (z dim 64, s dim 64)z-space test accuracy (lower is better): 72.20 -> 26.55Improved
use reverse cycle-consistency VAE instead of Szabo et al.specified/unspecified disentangling · MNIST (z dim 16, s dim 16)z-space test accuracy (lower is better): 96.08 -> 17.56Improved
use reverse cycle-consistency VAE instead of Mathieu et al.specified/unspecified disentangling · LineMod (z dim 64, s dim 256)z-space test accuracy (lower is better): 89.17 -> 57.17Improved
use reverse cycle-consistency VAE instead of Mathieu et al.specified/unspecified disentangling · LineMod (z dim 256, s dim 512)z-space test accuracy (lower is better): 86.46 -> 57.70Improved
use reverse cycle-consistency VAE instead of Mathieu et al.specified/unspecified disentangling · 2D Sprites (z dim 512, s dim 64)z-space test accuracy (lower is better): 11.98 -> 11.47No clear effect
use reverse cycle-consistency VAE instead of Mathieu et al.specified/unspecified disentangling · 2D Sprites (z dim 1024, s dim 512)z-space test accuracy (lower is better): 12.25 -> 11.61No clear effect
use reverse cycle-consistency VAE instead of Szabo et al.specified/unspecified disentangling · 2D Sprites (z dim 512, s dim 64)z-space test accuracy (lower is better): 99.63 -> 11.47Improved
increase latent dimensions from 16/16 to 64/64Ours · MNISTz-space test accuracy (lower is better): 17.56 -> 26.55Hurt
increase latent dimensions from 16/16 to 64/64Szabo et al. · MNISTz-space test accuracy (lower is better): 96.08 -> 98.14Hurt
use pairwise reverse-cycle loss instead of absolute distance to sampled z (ablation)Ours reverse cycle loss · MNIST/2D Sprites/LineModz-space test accuracy (lower is better)Improved

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