AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets

Damien Teney, LIN Yong, Seong Joon Oh, Ehsan Abbasnejad

NeurIPS 2023 · Label-efficient and robust learning › OOD and anomaly detection · approach: Out-of-distribution generalization theory · 7 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
train for more epochs (1 to 10) when re-training the last layer (ablation)DenseNet-121 linear probe (ERM) · WILDS-Camelyon17OOD accuracy vs ID accuracyMixed
add gradient-diversity loss to the linear classifiers (ablation)DenseNet-121 linear probe · WILDS-Camelyon17range of ID/OOD accuracyImproved
keep only models trained for a fixed 10 epochs and pool pretraining seeds (ablation)ERM models · WILDS-Camelyon17visible ID/OOD patternHurt
vary the re-training seed (ablation)ERM linear probe · WILDS-Camelyon17ID/OOD accuracyNo clear effect
vary the pretraining seed (ablation)DenseNet-121 · WILDS-Camelyon17OOD accuracyMixed
select epochs by ID validation accuracy instead of OODERM, mixup, class balancing methods · WildTime-arXiv and waterbirdsOOD accuracyHurt

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