AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Confidence Estimation via Auxiliary Models

Charles Corbière, Nicolas Thome, Antoine Saporta, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez

TPAMI 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 62 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 encoder fine-tuning to ConfidNet (ablation)ConfidNet · MNIST (SmallConvNet)AUPR (%): 44.54 -> 45.45Improved
add encoder fine-tuning to ConfidNet (ablation)ConfidNet · CIFAR-100 (VGG16)AUPR (%): 71.30 -> 73.55Improved
train ConfidNet on training set instead of validation set (ablation)ConfidNet · MNIST (MLP)AUPR (%): 38.22 -> 59.72Improved
train ConfidNet on training set instead of validation set (ablation)ConfidNet · CIFAR-100 (VGG16)AUPR (%): 73.82 -> 73.55No clear effect
use MSE loss on TCP instead of BCE (ablation)ConfidNet · CIFAR-10AUPR (%): 47.95 -> 49.94Improved
use MSE loss on TCP instead of ranking loss (ablation)ConfidNet · CIFAR-10AUPR (%): 44.04 -> 49.94Improved
use MSE loss instead of focal BCE (ablation)ConfidNet · CIFAR-10AUPR (%): 47.76 -> 49.94Improved
use ConfidNet instead of MCPMCP · CIFAR-100 (VGG16)AUPR (%): 71.30 -> 73.55Improved
use ConfidNet instead of MC DropoutMC Dropout · MNIST (SmallConvNet)AUPR (%): 42.12 -> 45.45Improved
add adversarial loss to ConfidNet (ablation)ConfidNet · GTA5->CityscapesmIoU (%): 47.6 -> 49.0Improved
add adversarial loss to multi-scale ConfidNet (ablation)Multi-scale ConfidNet · GTA5->CityscapesmIoU (%): 48.5 -> 49.9Improved
add multi-scale architecture to ConfidNet (ablation)ConfidNet · GTA5->CityscapesmIoU (%): 47.6 -> 48.5Improved

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