AI Paper Atlas

Research map / Continual learning / Class-incremental

Asymmetric Synthetic Data Update for Domain Incremental Dataset Distillation

Minyoung Oh, Jae-Young Sim

ICLR 2026 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention

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 asymmetric bi-level update to Finetune+Lstable (ablation)Proposed · R-MNIST (IPC=10), domains 1-5accuracy: 26.9 -> 36.3Improved
add asymmetric bi-level update to Finetune+Lstable (ablation)Proposed · R-MNIST (IPC=10), domains 16-20accuracy: 87.1 -> 94.5Improved
add asymmetric bi-level update to Finetune+Lstable (ablation)Proposed · R-MNIST (IPC=20), domains 11-15accuracy: 45.0 -> 72.9Improved
add stability loss Lstable to Finetune (ablation)Finetune · R-MNIST (IPC=10), domains 1-5accuracy: 33.4 -> 26.9Hurt
add stability loss Lstable to Finetune (ablation)Finetune · R-MNIST (IPC=10), domains 11-15accuracy: 23.7 -> 59.3Improved
add stability loss Lstable to Finetune (ablation)Finetune · R-MNIST (IPC=20), domains 16-20accuracy: 85.6 -> 77.5Hurt
use linear alpha/beta assignment instead of bi-level optimization (ablation)Proposed · R-MNIST (IPC=10), domains 1-5accuracy: 36.3 -> 31.0Hurt
use bi-level learned update rates instead of linear assignment (ablation)Proposed · R-MNIST (IPC=20), domains 1-5accuracy: 27.3 -> 32.9Improved
reduce distillation iterations to 1,000 (ablation)Proposed · PACS (IPC=10)accuracy: 48.0 -> 46.3Mixed
add proposed method over FinetuneProposed · PACS (IPC=10)average accuracy: 26.9 -> 48.0Improved
add proposed method over MASProposed · R-MNIST (IPC=10)average accuracy: 45.6 -> 62.7Improved
add proposed method over FinetuneProposed · Seq-CORe50 (IPC=20)forgetting: 79.2 -> 38.7Improved

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