AI Paper Atlas

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

AdaSCALE: Adaptive Scaling for OOD Detection

Sudarshan Regmi

ICML 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 0 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 Q' (Q plus correction term) instead of Q alone (ablation)AdaSCALE-A · ImageNet-1k near-OOD avg 8 archsFPR@95: 68.90 -> 61.17Improved
add Q' instead of Q alone (ablation)AdaSCALE-A · ImageNet-1k far-OOD avg 8 archsFPR@95: 42.63 -> 30.11Improved
add adaptive scaling on top of Q as OOD score (ablation)AdaSCALE-A · ImageNet-1k near-OOD ResNet-50FPR@95: 79.81 -> 59.43Improved
add the correction term to lambda*Q (balanced Q') (ablation)AdaSCALE-A · ImageNet-1k near-OOD ResNet-50FPR@95: 59.43 -> 58.97Improved
add Q to the correction-only OODness score (ablation)AdaSCALE-A · ImageNet-1k near-OOD ResNet-50FPR@95: 70.39 -> 58.97Improved
set perturbation magnitude to 0.5 instead of 0.1 (ablation)AdaSCALE-A · ImageNet-1k near-OOD ResNet-50FPR@95: 63.76 -> 58.97Improved
set perturbation magnitude to 0.5 instead of 1.0 (ablation)AdaSCALE-A · ImageNet-1k near-OOD ResNet-50FPR@95: 61.60 -> 58.97Improved
set k1 to 1% instead of 100% (ablation)AdaSCALE-A · ImageNet-1k near-OOD ResNet-50FPR@95: 60.99 -> 58.97Improved
set perturbed pixel fraction o to 5% instead of 100% (ablation)AdaSCALE-A · ImageNet-1k near-OOD ResNet-50FPR@95: 67.37 -> 58.97Improved
use 5000 instead of 10 ID validation samples for eCDF (ablation)AdaSCALE-A · ImageNet-1k near-OOD ResNet-50FPR@95: 59.69 -> 58.97No clear effect
add adaptive percentile to static scaling (AdaSCALE-A vs SCALE)AdaSCALE-A · ImageNet-1k near-OOD ResNet-50FPR@95: 67.76 -> 58.98Improved
tune only p_max with p_min fixed at 60 (ablation)AdaSCALE-A · ImageNet-1k near-OOD avg 8 archsFPR@95: 71.91 -> 62.29Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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