AI Paper Atlas

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

FAST: Topology-Aware Frequency-Domain Distribution Matching for Coreset Selection

Jin Cui, Boran Zhao, Jiajun Xu, Jiaqi Guo, Shuo Guan, Pengju Ren

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 1 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
use phase-decoupled CFD instead of standard CFD (ablation)FAST · DTDaccuracy (%): 41.15 -> 45.77Improved
use phase-decoupled CFD instead of standard CFD (ablation)FAST · RESISC-45accuracy (%): 82.01 -> 85.00Improved
use phase-decoupled CFD instead of standard CFD (ablation)FAST · CIFAR-10accuracy (%): 88.17 -> 90.32Improved
use PDAS instead of collinear frequency set (ablation)FAST · CIFAR-10 (10% keep)accuracy (%): 74.16 -> 90.32Improved
use PDAS instead of uniform sampling (ablation)FAST · CIFAR-10 (10% keep)accuracy (%): 86.60 -> 90.32Improved
use graph spectral features instead of pixel-level optimization (ablation)FAST · CIFAR-10 (10% keep)accuracy (%): 61.52 -> 90.32Improved
use graph spectral features instead of ResNet-50 features (ablation)FAST · CIFAR-10 (10% keep)accuracy (%): 81.51 -> 90.32Improved
use neighbor scale k=15 instead of k=5 (ablation)FAST · CIFAR-10 (10% keep)accuracy (%): 72.12 -> 90.32Improved
use reduced dimension d=32 instead of d=8 (ablation)FAST · CIFAR-10 (10% keep)accuracy (%): 78.86 -> 90.32Improved
use reduced dimension d=32 instead of d=128 (ablation)FAST · CIFAR-10 (10% keep)accuracy (%): 86.73 -> 90.32Improved
use PD-CFD instead of MSE as the distribution metric (ablation)FAST · CIFAR-10 (10% keep, ResNet18)accuracy (%): 9.16% accuracy dropImproved
use PD-CFD instead of KL as the distribution metric (ablation)FAST · CIFAR-10 (10% keep, ResNet18)accuracy (%): 7.15% accuracy dropImproved

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