AI Paper Atlas

Research map / Continual learning / Class-incremental

An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning

Quyen Tran, Hai Nguyen, Quan Dao, Hoang Phan, Linh Van, Khoat Than, Dinh Phung, Dimitris Metaxas, Trung Le

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 OTC instead of best baseline on CIFAR-10 at smallest memoryonline class-incremental learning · CIFAR-10, M=0.2kfinal average accuracy: 63.5 -> 64.8 (vs BiC+AC)Improved
use OTC on CIFAR-10 M=1k where it ties BiC+AC within noiseonline class-incremental learning · CIFAR-10, M=1kfinal average accuracy: 75.8±3.1 -> 76.1±2.0No clear effect
use OTC on Tiny-ImageNetonline class-incremental learning · Tiny-ImageNet, M=2kfinal average accuracy: 18.5 -> 19.5 (vs GSA)Improved
use OTC versus CoPE for forgettingonline class-incremental learning · Tiny-ImageNet, M=10kaverage forgetting: 8.2 -> 16.5 (CoPE vs OTC)Hurt
use OTC versus best baseline for forgetting on CIFAR-10online class-incremental learning · CIFAR-10, M=1kaverage forgetting: 10.0 -> 9.8 (vs GSA)Improved
use multiple centroids (4) per class instead of 1 (ablation)OTC · CIFAR-10, M=1000average accuracy: 71.6 -> 75.9Improved
increase centroids beyond optimum (4 to 8) (ablation)OTC · CIFAR-10, M=1000average accuracy: 75.9 -> 74.5Hurt
too many centroids with small memory (>3 at M=200) (ablation)OTC · CIFAR-10, M=0.2kaverage accuracyHurt
select replay buffer samples by MMOT centroids instead of randomly (ablation)OTC (4 centroids) · CIFAR-10, M=1000average accuracy: 73.4 -> 75.9Improved
centroid-based buffer selection with a single centroid (ablation)OTC (1 centroid) · CIFAR-10, M=1000average accuracy: 68.7 -> 71.6Improved

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