AI Paper Atlas

Research map / Detection and segmentation / CNN features

HierAmp: Coarse-to-Fine Autoregressive Amplification for Generative Dataset Distillation

Lin Zhao, Xinru Jiang, Xi Xiao, Qihui Fan, Lei Lu, Yanzhi Wang, Xue Lin, Octavia Camps, Pu Zhao, Jianyang Gu

CVPR 2026 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 7 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 class-token attention amplification at all scales (ablation)VAR distillation baseline · ImageNet-1K IPC=10Top-1 accuracy (%): 45.6 -> 47.6Improved
amplify only coarse scales (5-50%) versus only fine scales (ablation)HierAmp · ImageNet-1K IPC=10Top-1 accuracy (%): Fine 46.5 vs Coarse 47.6Improved
amplify mid scales only at 5-50% (ablation)HierAmp · ImageNet-1K IPC=10Top-1 accuracy (%): 45.6 -> 46.9Improved
amplify fine scales only at 7-50% (ablation)HierAmp · ImageNet-1K IPC=10Top-1 accuracy (%): 45.6 -> 46.3Improved
raise amplification from 3 regions (50%) to 5 regions (50%), full stages (ablation)HierAmp · ImageNet-1K IPC=10Top-1 accuracy (%): 47.1 -> 47.6Improved
increase top-region share from 30% to 70% (5 regions) at coarse stage (ablation)HierAmp · ImageNet-1K IPC=10Top-1 accuracy (%): 46.7 -> 47.0No clear effect
use very small coarse-stage amplification (0.1 vs 5) (ablation)HierAmp · ImageNet-1K IPC=10Top-1 accuracy (%): 0.1-5-5: 45.9; 5-0.1-5: 46.6Hurt
use HierAmp instead of D3HR on cross-arch ImageNet-1K IPC=10 (ResNet-18)HierAmp · ImageNet-1K IPC=10 cross-archTop-1 accuracy (%): 44.3 -> 44.6Improved
amplification effect on token diversity: coarse scales vs fine scales (ablation)HierAmp · ImageNet-1K IPC=50 token statisticscodebook token entropy / coverageMixed

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