AI Paper Atlas

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

Data-to-Model Distillation: Data-Efficient Learning Framework

Ahmad Sajedi, Samir Khaki, Lucy Z. Liu, Ehsan Amjadian, Yuri A. Lawryshyn, Konstantinos N. Plataniotis

ECCV 2024 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 6 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
distill into generator parameters with embedding matching loss (ablation)Pre-trained generator (BigGAN) · CIFAR-10 IPC 10accuracy improvement: +10.3%Improved
distill with prediction matching loss (ablation)Pre-trained generator (BigGAN) · CIFAR-10 IPC 10accuracy improvement: +7.9%Improved
combine embedding matching and prediction matching losses (ablation)Pre-trained generator (BigGAN) · CIFAR-10 IPC 10accuracy improvement: +12.7%Improved
distill into generator parameters instead of pixels so no re-distillation across IPCD2M · CIFAR-10 distillation cost (IPC1, 10, 50)total GPU hours: 47.4 -> 4.9Improved
raise softmax temperature T up to 4 (ablation)Prediction matching · CIFAR-10 IPC 10accuracyImproved
set task balance lambda too high (1000) or too low (ablation)D2M loss · CIFAR-10 IPC 10accuracyHurt
swap BigGAN for StyleGAN-XL as generator (ablation)D2M · CIFAR-10 IPC 50accuracy (%): 74.4 -> 75.2Improved
swap BigGAN for CGAN as generator (ablation)D2M · CIFAR-10 IPC 50accuracy (%): 74.4 -> 72.2Hurt
use D2M images on unseen architecturesD2M · CIFAR-10 IPC 50 cross-architectureaverage accuracy (%): 59.7 -> 63.6Improved
use D2M-generated proxy set for architecture search vs RandomD2M · CIFAR-10 NASbest-model test accuracy (%): 88.9 -> 88.9No clear effect
D2M for IPC 1 uses more GPU memory than pixel distillationD2M · CIFAR-10 IPC 1 distillationGPU hours: 1.4 -> 4.9Hurt

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