AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Addressing Failure Prediction by Learning Model Confidence

Charles Corbière, Nicolas THOME, Avner Bar-Hen, Matthieu Cord, Patrick Pérez

NeurIPS 2019 · Label-efficient and robust learning › Test-time adaptation · approach: Extrapolation and single-sample adaptation · 169 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 TCP confidence with ConfidNet instead of using the strongest reported baselinefailure prediction models · MNIST (MLP)AUPR-Error: 52.18 -> 57.37Improved
learn TCP confidence with ConfidNet instead of using the strongest reported baselinefailure prediction models · MNIST (Small ConvNet)AUPR-Error: 38.50 -> 45.89Improved
learn TCP confidence with ConfidNet instead of using the strongest reported baselinefailure prediction models · SVHN (Small ConvNet)AUPR-Error: 48.18 -> 50.72Improved
learn TCP confidence with ConfidNet instead of using the strongest reported baselinefailure prediction models · CIFAR-10 (VGG-16)AUPR-Error: 46.40 -> 49.94Improved
learn TCP confidence with ConfidNet instead of using the strongest reported baselinefailure prediction models · CIFAR-100 (VGG-16)AUPR-Error: 72.59 -> 73.68Improved
learn TCP confidence with ConfidNet instead of using the strongest reported baselinefailure prediction models · CamVid (SegNet)AUPR-Error: 49.35 -> 50.51Improved
add ConvNet fine-tuning after confidence training (ablation)ConfidNet · MNIST (Small ConvNet)AUPR-Error: 43.94% -> 45.89%Improved
add ConvNet fine-tuning after confidence training (ablation)ConfidNet · CIFAR-100 (VGG-16)AUPR-Error: 72.68% -> 73.68%Improved
replace MSE with BCE loss (ablation)ConfidNet · CIFAR-10 (VGG-16)AUPR-Error: 49.94% -> 47.95%Hurt
replace MSE with BCE loss (ablation)ConfidNet · CamVid (SegNet)AUPR-Error: 50.51% -> 48.96%Hurt
replace TCP with normalized TCPᵣ criterion (ablation)ConfidNet · CIFAR-10 (VGG-16)AUPR-Error: 49.94% -> 48.78%Hurt
replace TCP with normalized TCPᵣ criterion (ablation)ConfidNet · CamVid (SegNet)AUPR-Error: 50.51% -> 51.35%Improved

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