AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Balanced Dataset Distillation via Modeling Multiple Visual Pattern Distribution

Guanghui Shi, Xuefeng Liang, Qixiang Wen

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias

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
select samples from both pattern centers and margins in balance (BPS) instead of unbalanced selection (ablation)BPS coreset · ImageNet-1K IPC=50accuracy and MMDImproved
model multiple visual patterns per class and balance selection (BPS) vs CCFSBPS · CIFAR-10 IPC=50accuracy (%): 67.2 -> 77.1Improved
model-agnostic coreset selection for cross-architecture evaluationBPS · ImageNet-1K IPC=10, ViT-Saccuracy (%): 24.0 -> 30.2Improved
raise candidate ratio K from 10% to 20% (ablation)BPS · ImageNet-1K IPC=10accuracy (%): 51.9 -> 52.4Improved
raise candidate ratio K from 10% to 20% (ablation)BPS · CIFAR-100 IPC=10accuracy (%): 57.7 -> 57.1Hurt
raise candidate ratio K from 20% to 30% (ablation)BPS · ImageNet-1K IPC=10accuracy (%): 52.4 -> 51.6Hurt
use intermediate contrastive temperature tau1=0.5 instead of small or large values (ablation)BPS Stage 1 · CIFAR-10/CIFAR-100 IPC=10accuracyImproved
use intermediate distillation temperature tau2=20 instead of small or large values (ablation)BPS Stage 3 · CIFAR-10/CIFAR-100 IPC=10accuracyImproved
reuse one Stage 1 optimization across IPC budgets (Optimize-Once-for-All-IPCs)BPS · CIFAR-100 distillation timetime costImproved

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