AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Active Generation for Image Classification

Tao Huang, Jiaqi Liu, Shan You, Chang Xu

ECCV 2024 · Image generation › Fast diffusion sampling · approach: Distributional control of diffusion · 8 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
generate images guided by misclassified validation samples (ActGen) instead of random fixed-prompt generation with the same budget (ablation)ResNet-50 on ImageNet · ImageNet-1k valtop-1 accuracy (%): 76.64 -> 78.65Improved
add image guidance from real hard images (ablation)random SD generation · ImageNet-1k val (ResNet-50)top-1 accuracy (%): 76.64 -> 77.93Improved
add attention-mask selective guidance (AIG) (ablation)ActGen image guidance · ImageNet-1k val (ResNet-50)top-1 accuracy (%): 77.93 -> 78.15Improved
add contrastive loss against memory bank (ablation)ActGen · ImageNet-1k val (ResNet-50)top-1 accuracy (%): 78.15 -> 78.36Improved
add adversarial classification loss (ablation)ActGen · ImageNet-1k val (ResNet-50)top-1 accuracy (%): 78.36 -> 78.65Improved
increase validation set size from 0.1K/1K to 5K or more (ablation)ActGen · ImageNet-1k val (ResNet-50)top-1 accuracy (%)Improved
use ActGen with 10% generated images instead of 94% generated images (Azizi et al.)ResNet-50 on ImageNet · ImageNet-1k valtop-1 accuracy (%): 78.17 -> 78.65Improved
apply ActGen on CIFAR-100 with ResNet-50ActGen · CIFAR-100 (ResNet-50)top-1 accuracy (%): 77.06 -> 77.33No clear effect
use ActGen instead of Real filtering at 1-shot on EuroSATfew-shot EuroSAT · EuroSAT 1-shot (2K generated)accuracy (%): 70.32 -> 66.78Hurt
increase synthetic images beyond about 1,850 for few-shot Pets baseline (ablation)Real guidance baseline · Pets 1-shotaccuracy (%): 87.65 -> 87.41Hurt
reimplement Azizi et al. on Stable Diffusion rather than ImagenAzizi et al. · ImageNet-1k val (ResNet-50)top-1 accuracy (%): 78.17 -> 76.83Hurt

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