AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Invariant-Equivariant Representation Learning for Multi-Class Data

Ilya Feige

ICML 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 1 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 invariant embedding for classification instead of the dedicated benchmark classifierEquiVAE on MNIST · MNIST test (supervised)error rate: 0.84 ± 0.03 -> 0.82 ± 0.03Improved
Use the invariant embedding for classification instead of the dedicated benchmark classifierEquiVAE on SVHN · SVHN test (supervised)error rate: 10.04 ± 0.14 -> 11.97 ± 0.34Hurt
Use the invariant embedding distance classifier instead of the dedicated benchmark classifierEquiVAE on MNIST · MNIST test (supervised)error rate: 0.84 ± 0.03 -> 0.82 ± 0.05Improved
Use the invariant embedding distance classifier instead of the dedicated benchmark classifierEquiVAE on SVHN · SVHN test (supervised)error rate: 10.04 ± 0.14 -> 12.30 ± 0.28Hurt
Train the classifier jointly with the semi-supervised EquiVAE objective rather than on labelled data aloneEquiVAE · MNIST, 100 labelserror rate: 21.91± 0.66 -> 8.90± 0.70Improved
Train the classifier jointly with the semi-supervised EquiVAE objective rather than on labelled data aloneEquiVAE · MNIST, 600 labelserror rate: 6.64± 0.35 -> 3.99± 0.17Improved
Train the classifier jointly with the semi-supervised EquiVAE objective rather than on labelled data aloneEquiVAE · MNIST, 1000 labelserror rate: 5.43± 0.31 -> 3.34± 0.17Improved
Train the classifier jointly with the semi-supervised EquiVAE objective rather than on labelled data aloneEquiVAE · MNIST, 3000 labelserror rate: 2.96± 0.11 -> 2.23± 0.14Improved
Train the classifier jointly with the semi-supervised EquiVAE objective rather than on labelled data aloneEquiVAE · SVHN, 1000 labelserror rate: 39.64 ± 1.47 -> 37.95 ± 0.66Improved
Train the classifier jointly with the semi-supervised EquiVAE objective rather than on labelled data aloneEquiVAE · SVHN, 3000 labelserror rate: 25.50 ± 0.91 -> 24.95 ± 0.57Improved
Allow the invariant representation to receive the target x directly instead of using complementary same-class samples (ablation)EquiVAE generative model · MNIST and SVHN (unsupervised training)reconstruction of within-class structureHurt

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