AI Paper Atlas

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

DOCTOR: A Simple Method for Detecting Misclassification Errors

Federica Granese, Marco Romanelli, Daniele Gorla, Catuscia Palamidessi, Pablo Piantanida

NeurIPS 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 9 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
use all softmax probabilities (sum of squares) instead of only the maximum (SR)DOCTOR D_alpha (TBB) · AmazonFashionFRR at 95% TRR (%): 50.1 -> 27.1Improved
use all softmax probabilities instead of only the maximum (SR)DOCTOR D_alpha (TBB) · CIFAR10AUROC (%): 93.8 -> 94Improved
use all softmax probabilities instead of only the maximum (SR)DOCTOR D_alpha (TBB) · TinyImageNetAUROC (%): 84.9 -> 84.9No clear effect
add input perturbation (PBB) to DOCTOR D_alpha (ablation)DOCTOR D_alpha · CIFAR10FRR at 95% TRR (%): 17.9 -> 13.9Improved
add input perturbation (PBB) to DOCTOR D_alpha (ablation)DOCTOR D_alpha · CIFAR10AUROC (%): 94 -> 95.2Improved
use D_alpha instead of D_beta in TBB (ablation)DOCTOR · CIFAR10AUROC (%): 68.5 -> 94Improved
use D_alpha instead of D_beta in PBB (ablation)DOCTOR · CIFAR10AUROC (%): 94.8 -> 95.2Improved
use DOCTOR instead of ODIN in PBBDOCTOR D_alpha · CIFAR10FRR at 95% TRR (%): 18.4 -> 13.9Improved
use DOCTOR instead of ODIN in PBBDOCTOR D_alpha · CIFAR100AUROC (%): 87.1 -> 88.2Improved
use DOCTOR instead of Mahalanobis (MHLNB) in PBBDOCTOR D_alpha · CIFAR100AUROC (%): 50 -> 88.2Improved
use DOCTOR instead of ODIN with OOD samples mixed inDOCTOR D_alpha · CIFAR10 + iSUN (1 in 5 OOD)AUROC (%): 94.6 -> 95.4Improved

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