AI Paper Atlas

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

Distill Gold from Massive Ores: Bi-level Data Pruning towards Efficient Dataset Distillation

Yue Xu, Yong-Lu Li, Kaitong Cui, Ziyu Wang, Cewu Lu, Yu-Wing Tai, Chi-Keung Tang

ECCV 2024 · Label-efficient and robust learning › Knowledge distillation · approach: Self and data-free distillation · 9 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
prune real data by empirical loss before distillation (ablation)DC, CIFAR10 IPC=1 · CIFAR10 IPC=1 (DC)accuracy (%): 28.3 -> 29.7 at 99% pruningImproved
random pruning of real data before distillation (ablation)DC, CIFAR10 IPC=1 · CIFAR10 IPC=1 (DC)maximum pruning ratio: 90%No clear effect
replace random with empirical-loss pruning on DC CIFAR10 IPC=1 (ablation)DC · CIFAR10 IPC=1maximum pruning ratio: 90% -> 99.5%Improved
use empirical-loss pruning on MTT/IDC/IDM at larger IPC (ablation)MTT, IDC, IDM · CIFAR10 IPC=10maximum pruning ratio: IDM 10% -> 10%Mixed
add adaptive ITE-based pruning on top of preemptive pruning (ablation)BiLP with IDC · CIFAR10 IPC=10top-1 accuracy (%): 68.5 -> 69.2Improved
prune both small and large ITE instead of one direction (ablation)BiLP · CIFAR100 IPC=1top-1 accuracy (%): 29.8 -> 30.1Improved
add Taylor approximation of ITE (ablation)ITE computation · CIFAR10 IPC=10total iteration time (s/iter): 23.38 -> 0.65Improved
add lazy selection (update every 10 iterations) (ablation)BiLP · CIFAR10 IPC=10total iteration time (s/iter): 0.65 -> 0.47Improved
apply BiLP to DC and IDCDC, IDC · CIFAR10 IPC=1top-1 accuracy (%): 50.6 -> 51.5Improved
use larger multi-formation factor (x3) with BiLP (ablation)BiLP+IDC · CIFAR100 IPC=1top-1 accuracy (%): 30.1 -> 34.0Improved
apply BiLP preemptive pruning to DM on ImageNet-1KDM · ImageNet-1K IPC=10accuracy (%): 3.86 -> 5.21Improved
use empirical loss pruning instead of coreset methods CRAIG, GradMatch, GLISTER (ablation)DC, CIFAR10 IPC=50 · CIFAR10 IPC=50 pruning 70%accuracy (%): 49.0 -> 54.1Improved

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