AI Paper Atlas

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

Expert load matters: operating networks at high accuracy and low manual effort

Sara Sangalli, Ertunc Erdil, Ender Konukoglu

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 3 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 AUCOCL to cross-entropyResNet-50 · CIFAR100AUCOC: 91,10 -> 93,81Improved
Add AUCOCL to cross-entropyResNet-50 · CIFAR100accuracy: 73,69 -> 75,94Improved
Add AUCOCL to cross-entropyResNet-50 · CIFAR100 at 90% accuracyτ₀: 34,72 -> 28,39Improved
Add AUCOCL to cross-entropyWideResnet-28-10 · Tiny-ImageNetAUCOC: 74,03 -> 76,64Improved
Add AUCOCL to cross-entropyWideResnet-28-10 · Tiny-ImageNetaccuracy: 49,29 -> 51,40Improved
Add AUCOCL to cross-entropyResNet-50 · ImageNetAUCOC: 36,04 -> 40,43Improved
Add AUCOCL to cross-entropyResNet-50 · ImageNetaccuracy: 20,19 -> 23,36Improved
Add AUCOCL to cross-entropyResNet-50 · SVHN OODAUROC: 81,64 -> 86,56Improved

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