AI Paper Atlas

Research map / Continual learning / Class-incremental

Geometry-driven OOD Detectors Are Class-Incremental Learners

Wangwang Jia, Zijian Gao, Tianjiao Wan, Yuan Cao, Yong Dou, Kele Xu

CVPR 2026 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning

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 refined top-k sparse task activation instead of coarse single-pass inference (ablation)GOD · ImageNet-R (T=5)average incremental accuracy: 85.31 -> 86.90Improved
use refined top-k sparse activation instead of activating all task LoRA blocks (ablation)GOD · ImageNet-R (T=5)average incremental accuracy: 86.74 -> 86.90No clear effect
use refined mode instead of coarse mode (ablation)GOD · ImageNet-A (T=5)inference time (s): 3.79 -> 9.24Hurt
vary top-k from 2 to 5 (ablation)GOD (Refined) · ImageNet-R (T=10)average incremental accuracy: 84.85 -> 85.41 (k=2 to 3), 85.16 at k=5No clear effect
replace learnable linear/cosine head with fixed ETF anchors plus ArcFace (ablation)GOD · Stanford Cars / ImageNet-R (two tasks)task-ID confidence gapImproved
add ArcFace loss on top of ETF loss (ablation)GOD · Stanford Cars (t-SNE, qualitative)cluster compactnessImproved
add random projection on top of ETF loss (ablation)GOD · Stanford Cars (t-SNE, qualitative)global class separationImproved
combine ETF loss, ArcFace and random projection (ablation)GOD · Stanford Cars (t-SNE, qualitative)cluster qualityImproved
share shallow 9 LoRA blocks across tasks and use task-specific deep 3 blocksGOD · ImageNet-A (T=5)trainable parameters (M): 4.73 -> 2.64Improved
GOD versus strongest baseline on CIFAR-100GOD (Refined) · CIFAR-100 (T=10)average incremental accuracy: 92.01 -> 92.87No clear effect

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