AI Paper Atlas

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

Dataset Distillation by Automatic Training Trajectories

Dai Liu, Jindong Gu, Hu Cao, Carsten Trinitis, Martin Schulz

ECCV 2024 · Label-efficient and robust learning › Knowledge distillation · approach: Self and data-free distillation · 28 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
replace fixed trajectory length with automatic (minimum-distance) trajectory lengthMTT/FTD · CIFAR-10 IPC=10 cross-architecture (VGG11)test accuracy: 47.0 -> 54.2Improved
replace fixed trajectory length with automatic trajectory lengthFTD · CIFAR-10 IPC=50 cross-architecture (AlexNet)test accuracy: 53.8 -> 60.0Improved
replace fixed trajectory length with automatic trajectory lengthFTD · CIFAR-10 IPC=10 (ConvNet)test accuracy: 66.6 -> 67.7Improved
replace fixed trajectory length with automatic trajectory lengthFTD · ImageMeow IPC=10test accuracy: 43.3 -> 45.5Improved
replace fixed trajectory length with automatic trajectory lengthFTD · Tiny ImageNet IPC=10test accuracy: 24.5 -> 25.8Improved
use ATT instead of KIP on CIFAR-10 IPC=1KIP · CIFAR-10 IPC=1test accuracy: 49.9 -> 48.3Hurt
use ATT instead of fixed trajectory length under learning-rate perturbations (ablation)vanilla LDD · parameter variation (lr img, lr step size)successful runs out of 20Improved
use ATT instead of fixed trajectory lengthvanilla LDD · CIFAR-10 IPC=1time per iteration: 0.8s vs 0.8sNo clear effect
increase trajectory bound N_S for ATT (30, 50, 70, up to 130) (ablation)ATT · CIFAR-10 IPC=1test accuracyImproved
add error tolerance gamma to fixed-length matching (ablation)FTL · CIFAR-10 IPC=1 (N_S=50)step selection errorsNo clear effect

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