AI Paper Atlas

Research map / Continual learning / Class-incremental

Continual Out-of-Distribution Detection with Analytic Neural Collapse

Saleh Momeni, Changnan Xiao, Bing Liu

AAAI 2026 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 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 class-variation collapse (NC1) on top of random projection (ablation)AnaNC · CUB in-dataset OODAUC: 70.61 -> 78.56Improved
add simplex ETF arrangement (NC2) on top of NC1 (ablation)AnaNC · CUB in-dataset OODAUC: 78.56 -> 83.07Improved
add simplex ETF arrangement (NC2) on top of NC1 (ablation)AnaNC · Cars in-dataset OODAUC: 69.52 -> 81.76Improved
add simplex ETF arrangement (NC2) on top of NC1 (ablation)AnaNC · Cars in-dataset OODFPR95: 87.61 -> 76.13Improved
add NC1 on top of random projection (ablation)AnaNC · CIFAR100 in-dataset OODAUC: 85.09 -> 86.30Improved
add random projection alone to NCM on PTM features (ablation)NCM · CUB in-dataset OODAUC: 71.18 -> 70.61No clear effect
add random projection alone to NCM on PTM features (ablation)NCM · Cars in-dataset OODAUC: 58.68 -> 59.14No clear effect
increase random projection dimension D (ablation)AnaNC · In-dataset OOD, DINOAUCImproved
use AnaNC instead of best baseline (in-dataset, DINO)AnaNC · In-dataset OOD averageAUC: 2.22% in AUC and 3.24% in FPR95Improved
use AnaNC instead of best baseline (in-dataset, MOCO)AnaNC · In-dataset OOD averageAUC: 1.51% in AUC and 4.38% in FPR95Improved
use AnaNC instead of strongest baseline (cross-dataset, DINO)AnaNC · Cross-dataset OOD averageAUC: 0.49% in AUC and 0.88% in FPR95Improved
use AnaNC instead of strongest baseline (cross-dataset, MOCO)AnaNC · Cross-dataset OOD averageAUC: 0.86% in AUC and 1.94% in FPR95Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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