AI Paper Atlas

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

Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data

Utkarsh Ojha, Krishna Kumar Singh, Cho-Jui Hsieh, Yong Jae Lee

NeurIPS 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 14 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
Learn the categorical prior and add full contrastive lossInfoGAN · MNIST, YTF, 3D Cars, 3D Chairs, ShapeNetNMI: 0.777 -> 0.889; 0.666 -> 0.792; 0.499 -> 0.850; 0.253 -> 0.650; 0.638 -> 0.790Improved
Add positive-pair contrastive loss to learned-prior InfoGAN (ablation)Gumbel-Softmax InfoGAN · MNIST, YTF, 3D Cars, 3D Chairs, ShapeNetNMI: 0.836 -> 0.878; 0.760 -> 0.765; 0.400 -> 0.582; 0.236 -> 0.454; 0.603 -> 0.724Improved
Add negative-pair contrastive constraints (ablation)Gumbel-Softmax + pos-L_ntxent · MNIST, YTF, 3D Cars, 3D Chairs, ShapeNetNMI: 0.878 -> 0.889; 0.765 -> 0.792; 0.582 -> 0.850; 0.454 -> 0.650; 0.724 -> 0.790Improved
Add contrastive loss to Ground-truth InfoGAN (ablation)Ground-truth InfoGAN · MNIST, YTF, 3D Cars, 3D ChairsNMI: 0.783 -> 0.801; 0.694 -> 0.742; 0.451 -> 0.784; 0.174 -> 0.592Improved
Use learned prior instead of fixed ground-truth prior (ablation)InfoGAN · MNIST, YTF, 3D Cars, 3D Chairs, ShapeNetNMI: 0.783 vs 0.836; 0.694 vs 0.760; 0.451 vs 0.400; 0.174 vs 0.236; 0.549 vs 0.603Mixed
Learn a categorical prior and use full contrastive lossInfoGAN · MNIST, YTF, 3D Cars, 3D Chairs, ShapeNetENT: 0.457 -> 0.213; 1.031 -> 0.636; 1.108 -> 0.303; 1.663 -> 0.765; 0.531 -> 0.297Improved
Use Elastic-InfoGAN features rather than Uniform InfoGAN features1NN classification · MNIST, YTF, 3D Cars, 3D Chairsaccuracy: 0.8665 -> 0.9655; 0.9581 -> 0.9985; 0.7700 -> 0.9852; 0.6438 -> 0.9515Improved

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