AI Paper Atlas

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

Meta-Cal: Well-controlled Post-hoc Calibration by Ranking

Xingchen Ma, Matthew B. Blaschko

ICML 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Confidence calibration objectives · 2 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
Augment temperature scaling with ranking-based miscoverage controlMeta-Cal on CIFAR10 · CIFAR10, DenseNet40ECE: 0.00510 -> 0.00434Improved
Augment temperature scaling with ranking-based coverage-accuracy controlMeta-Cal on CIFAR10 · CIFAR10, DenseNet40ECE: 0.00510 -> 0.00355Improved
Use coverage-accuracy control rather than miscoverage controlMeta-Cal · CIFAR10, DenseNet40ECE: 0.00434 -> 0.00355Improved
Use coverage-accuracy control rather than miscoverage controlMeta-Cal · CIFAR100, ResNet110ECE: 0.01815 -> 0.01441Improved
Use coverage-accuracy control rather than miscoverage controlMeta-Cal · CIFAR100, WideResNet32ECE: 0.01332 -> 0.01189Hurt
Apply Meta-Cal with either control variant instead of the strongest listed baselineMeta-Cal · CIFAR100, ResNet110ECE: GPC 0.01348; MetaMis 0.01815; MetaAcc 0.01441Mixed
Apply Meta-Cal with coverage-accuracy control instead of temperature scalingMeta-Cal · ImageNet, ResNet152ECE: 0.02023 -> 0.01138Improved

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