AI Paper Atlas

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

Learning latent representations across multiple data domains using Lifelong VAEGAN

Fei Ye, Adrian G. Bors

ECCV 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Disentangled and discrete latent models · 76 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 inference model with VAE and GAN hybrid (L-VAEGAN) instead of VAE-based LGMlifelong generative replay · MNIST (M-F)reconstruction MSE: 7.18 -> 4.75Improved
use L-VAEGAN instead of LGMlifelong generative replay · MNIST (M-F)classification accuracy: 91.26 -> 92.53Improved
use L-VAEGAN instead of VAEGAN with GRMlifelong generative replay · Fashion (M-F)reconstruction MSE: 17.03 -> 17.44Hurt
use L-VAEGAN instead of LGMlifelong generative replay · Fashion (F-M)reconstruction MSE: 18.83 -> 13.16Improved
use L-VAEGAN instead of VAEGANlifelong generative replay · Fashion (F-M)classification accuracy: 64.98 -> 66.97Improved
add generative replay samples (GRM) during lifelong training (ablation)semi-supervised L-VAEGAN · MNIST to Fashion accuracyaccuracyImproved
use L-VAEGAN instead of EWClifelong supervised · MNIST (M-F)accuracy: 37.7 -> 98.76Improved
use L-VAEGAN instead of EWClifelong supervised · MNIST (F-M)accuracy: 99.12 -> 98.77Hurt
use L-VAEGAN instead of Transferlifelong supervised · SVHN (M-S)accuracy: 89.90 -> 81.97Hurt
use L-VAEGAN instead of LGANlifelong supervised · SVHN (S-M)accuracy: 76.76 -> 80.99Improved
use L-VAEGAN instead of LGANsemi-supervised lifelong · MNIST errorclassification error: 5.46 -> 4.34Improved
use lifelong L-VAEGAN instead of non-lifelong M1+M2semi-supervised · MNIST errorclassification error: 2.40 -> 4.34Hurt

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