AI Paper Atlas

Research map / Continual learning / Class-incremental

A Tiny Change, A Giant Leap: Long-Tailed Class-Incremental Learning via Geometric Prototype Alignment

Xinyi Lai, Luojun Lin, Weijie Chen, Yuanlong Yu

ICCV 2025 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 2 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 GPA to LUCIRLUCIR · CIFAR-100-LT shuffled LT-CIL (5 tasks)average accuracy (%): 35.09 -> 44.68Improved
add GPA to CODA-PromptCODA-Prompt · CIFAR-100-LT shuffled LT-CIL (5 tasks)average accuracy (%): 65.35 -> 79.20Improved
add GPA to EASEEASE · CIFAR-100-LT shuffled LT-CIL (5 tasks)average accuracy (%): 87.12 -> 89.23Improved
add GPA to L2PL2P · CIFAR-100-LT shuffled LT-CIL (5 tasks)average accuracy (%): 65.83 -> 64.85Hurt
use GPA instead of GVAlign with LUCIRLUCIR · CIFAR-100-LT shuffled LT-CIL (5 tasks)average accuracy (%): 42.80 -> 44.68Improved
add GPA to DualPrompt on ordered LT-CILDualPrompt · CIFAR-100-LT ordered LT-CIL (5 tasks)average accuracy (%): 54.55 -> 76.65Improved
add geometric prototype alignment (Phase 2 initialization) (ablation)GPA · CIFAR-100-LT ablation of GPAaverage accuracy (%): 40.12 -> 44.68Improved
add geometric prototype alignment (Phase 2 initialization) (ablation)GPA · CIFAR-100-LT ablation of GPAfinal task accuracy (%): 29.8 -> 35.4Improved
add geometric prototype alignment (Phase 2 initialization) (ablation)GPA · CIFAR-100-LT ablation of GPAforgetting rate: 15.1 -> 6.94Improved
add dynamic anchoring (Phase 3) (ablation)GPA · CIFAR-100-LT ablation of GPAforgetting rate: 20.6 -> 6.94Improved
add dynamic anchoring (Phase 3) (ablation)GPA · CIFAR-100-LT ablation of GPAaverage accuracy (%): 42.05 -> 44.68Improved
add dynamic anchoring (Phase 3) (ablation)GPA · CIFAR-100-LT ablation of GPAfinal task accuracy (%): 32.1 -> 35.4Improved

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