AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Towards Model-Agnostic Dataset Condensation by Heterogeneous Models

Jun-Yeong Moon, Jung Uk Kim, Gyeong-Moon Park

ECCV 2024 · Image generation › Autoregressive and latent generation · approach: Synthetic training data from generators · 3 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
condense with heterogeneous models (ConvNet + ViT-tiny) instead of a single ConvNetdataset condensation baselines (IDC, DREAM) · CIFAR-10 (IPC 10)average accuracy across models: 48.17 -> 75.04 (DREAM vs HMDC)Improved
add Gradient Balance Module and Mutual Distillation together (ablation)HMDC · CIFAR-10 (IPC 10)ViT average accuracy: 81.25 -> 82.64Improved
add only Gradient Balance Module (ablation)HMDC · CIFAR-10 (IPC 10)average accuracy across models: 74.05 -> 71.68Hurt
add only Mutual Distillation (ablation)HMDC · CIFAR-10 (IPC 10)average accuracy across models: 74.05 -> 73.60No clear effect
add both GBM and MD (ablation)HMDC · CIFAR-10 (IPC 10)average accuracy across models: 74.05 -> 74.85No clear effect
condense with ViT-tiny only instead of ConvNet only (ablation)DREAM · CIFAR-10 (IPC 10)accuracy on ConvNet: 47.62 -> 25.69Hurt
use HMDC instead of DREAM at IPC 1dataset condensation · CIFAR-10 (IPC 1)average accuracy across models: 18.00 -> 48.87Improved
use HMDC at IPC 50dataset condensation · CIFAR-10 (IPC 50)average accuracy across models: 79.13 (Random) -> 79.66No clear effect
condense with two heterogeneous models while needing only 100 iterationsHMDC · CIFAR-10iterations: 100 iterations versus 1,200 to 20,000Improved

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