AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

Understanding Dataset Distillation via Spectral Filtering

Deyu Bo, Songhua Liu, Xinchao Wang

ICLR 2026 · Label-efficient and robust learning › Knowledge distillation · approach: Patient consistent distillation · 3 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 signal-matching loss to filter-matching loss (ablation)CFM · CIFAR-100 IPC=50accuracy: 64.95 -> 67.32Improved
add classification loss on top of filter+signal losses (ablation)CFM · CIFAR-100 IPC=50accuracy: 67.32 -> 72.48Improved
add classification loss on top of filter+signal losses (ablation)CFM · ImageNet-1k IPC=50accuracy: 55.76 -> 57.32Improved
add signal-matching loss (ablation)CFM · Tiny-ImageNet IPC=50accuracy: 51.20 -> 51.92Improved
use curriculum high-pass filter (CFM) vs fixed filters (ablation)CFM · Tiny-ImageNet / ImageNet-1kaccuracyImproved
use low-pass filter instead of high-pass (ablation)CFM · Tiny-ImageNet / ImageNet-1kaccuracyHurt
use extremely high-frequency filter beta=1e-4 (ablation)CFM · Tiny-ImageNet / ImageNet-1kaccuracyHurt
CFM vs RDED at low budgetCFM · ImageNet-1k IPC=10 (ResNet-18)accuracy: 42.0 (RDED) vs 40.6 (CFM)Hurt
CFM vs RDED at low budgetCFM · Tiny-ImageNet IPC=50 (ResNet-18)accuracy: 58.2 (RDED) vs 58.0 (CFM)Hurt
CFM vs FrePo/MTT on small datasetCFM · CIFAR-10 IPC=10 (ConvNet-128)accuracy: 65.5 (FrePo) vs 52.1 (CFM)Hurt
CFM vs DWACFM · CIFAR-100 IPC=10 (ConvNet-128)accuracy: 47.6 -> 58.3Improved
CFM vs G-VBSM across architecturesCFM · ImageNet-1k IPC=50, DenseNet-121accuracy: 58.47 -> 60.91Improved

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