AI Paper Atlas

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

Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

Yaodong Yu, Kwan Ho Ryan Chan, Chong You, Chaobing Song, Yi Ma

NeurIPS 2020 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Representation evaluation and trade-offs · 67 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
Train the same network with MCR² rather than cross-entropyResNet-18 features · CIFAR10, label corruption 0.5classification accuracy: 60.37% -> 84.30%Improved
Train the same network with MCR² rather than cross-entropyResNet-18 features · CIFAR10, label corruption 0.1classification accuracy: 90.91% -> 91.16%Improved
Control the expansion and compression rates during MCR² training (ablation)MCR² self-supervised clustering · CIFAR10ACC: 0.570 -> 0.684Improved
Use MCR²-Ctrl rather than DCCMSelf-supervised clustering · CIFAR10ACC: 0.623 -> 0.684Improved
Use MCR²-Ctrl rather than DCCMSelf-supervised clustering · CIFAR100ARI: 0.173 -> 0.167Hurt
Use MCR²-Ctrl rather than DCCMSelf-supervised clustering · STL10ACC: 0.482 -> 0.491Improved

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