AI Paper Atlas

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

DREAM: Efficient Dataset Distillation by Representative Matching

Yanqing Liu, Jianyang Gu, Kai Wang, Zheng Zhu, Wei Jiang, Yang You

ICCV 2023 · Label-efficient and robust learning › Knowledge distillation · approach: Self and data-free distillation · 93 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 representative matching (sub-cluster sampling of original images) (ablation)IDC · CIFAR10 IPC 10top-1 accuracy (%): 67.5 -> 68.9Improved
Add clustering-based initialization (ablation)IDC · CIFAR10 IPC 10top-1 accuracy (%): 67.5 -> 68.1Improved
Combine representative matching and clustering initialization (ablation)IDC · CIFAR10 IPC 10top-1 accuracy (%) and iterations: 67.5 -> 69.4; 1000 -> 150 iterationsImproved
Plug DREAM into DCDC · CIFAR10 IPC 10top-1 accuracy (%): 44.9 -> 45.9Improved
Plug DREAM into DSADSA · CIFAR10 IPC 10top-1 accuracy (%): 52.1 -> 53.1Improved
Use DREAM-distilled data on unseen architecture ResNet-10IDC distilled on ConvNet-3 · CIFAR10 IPC 10 cross-architecturetop-1 accuracy (%): 63.5 -> 66.3Improved
Increase sub-cluster number from 32 to 128 (ablation)DREAM · CIFAR10 IPC 10top-1 accuracy (%): 67.2 -> 69.4Improved
Increase sub-cluster number from 128 to 256 (ablation)DREAM · CIFAR10 IPC 10top-1 accuracy (%): 69.4 -> 68.9Hurt
Draw more than one sample per sub-cluster (ablation)DREAM · CIFAR10 IPC 10, N=32top-1 accuracy (%): 67.2 -> 67.7No clear effect
Use DREAM instead of DSA at larger IPC on FashionMNISTDREAM · FashionMNIST IPC 50top-1 accuracy (%): 88.7 -> 86.8Hurt

Later papers that compared with this method

4 later accepted papers report DREAM as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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