AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Generalized Multimodal ELBO

Thomas M. Sutter, Imant Daunhawer, Julia E Vogt

ICLR 2021 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervised speech and brain decoding · 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
Use the MoPoE posterior instead of the MVAE posteriorMultimodal VAE · MNIST-SVHN-Text (all modalities)latent classification accuracy: 0.96 ±0.02 -> 0.98 ±0.01Improved
Use the MoPoE posterior instead of the MMVAE posteriorMultimodal VAE · MNIST-SVHN-Text (all modalities)generation coherence: 0.28 -> 0.31Improved
Use the MoPoE posterior instead of the MVAE posteriorMultimodal VAE · MNIST-SVHN-Text (joint)test log-likelihood: -1790 ±3.3 -> -1819 ±5.7Hurt
Use the MoPoE posterior instead of the MMVAE posteriorMultimodal VAE · CelebA (image and text; joint latent)mean average precision: 0.35 -> 0.39Improved
Use the MoPoE posterior instead of the MMVAE posteriorMultimodal VAE · CelebA (image to text)generation mean average precision: 0.14 -> 0.15Mixed
Use the MoPoE posterior instead of the MMVAE posteriorMultimodal VAE · CelebA (text to image)generation mean average precision: 0.41 -> 0.43Improved
Use the MoPoE posterior instead of the MMVAE posteriorMultimodal VAE · PolyMNIST (joint generation)joint coherence: 20.0 (±1.9) -> 12.1 (±1.6) percentHurt
Optimize posterior approximations for all modality subsetsMoPoE-VAE · PolyMNISTconditional coherenceImproved
Combine subset PoEs with a mixture over subsets rather than using only the full-set PoEMultimodal VAE · MNIST-SVHN-Textgeneration coherence: 0.12 -> 0.31Improved

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