AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Difficulty Controlled Diffusion Model for Synthesizing Effective Training Data

Zerun Wang, Jiafeng Mao, Xueting Wang, Toshihiko Yamasaki

AAAI 2026 · Image generation › Fast diffusion sampling · approach: Distributional control of diffusion · 5 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 medium-difficulty synthetic data instead of easy synthetic dataReal + synthetic training data · Imagenetteaccuracy (%): 95.2 (+0.2) -> 95.8 (+0.8)Improved
add extremely hard synthetic dataReal + synthetic training data · Imagenetteaccuracy (%): 95.0 -> 94.6 (-0.4)Hurt
use difficulty-conditioned generation instead of Real-FakeSynthetic data generator · ImageNet (10% synthetic)top-1 accuracy (%): 78.61 -> 78.74Improved
use difficulty-conditioned generation instead of Real-FakeSynthetic data generator · ImageNet (100% synthetic)top-1 accuracy (%): 78.62 -> 78.63No clear effect
fine-tune Stable Diffusion with LoRA instead of no fine-tuningStable Diffusion synthetic data · ImageNet (10% synthetic)top-1 accuracy (%): 77.90 -> 78.61Improved
use difficulty-conditioned generation instead of Real-Fake with ViT-smallSynthetic data generator · Imagenette (75% synthetic)accuracy (%): 84.8 -> 86.0Improved
use difficulty-conditioned generation instead of Real-Fake with ResNet-50Synthetic data generator · Imagenette (75% synthetic)accuracy (%): 95.4 -> 96.4Improved
use difficulty-conditioned generation instead of Real-Fake with ResNet-101Synthetic data generator · Imagenette (75% synthetic)accuracy (%): 95.8 -> 96.8Improved
set mean difficulty score to 0.5 rather than 0.3 (ablation)Difficulty score sampling · Imagenette (75% synthetic)accuracy (%): 95.8 -> 96.4Improved
raise mean difficulty score from 0.5 to 0.9 (ablation)Difficulty score sampling · Imagenette (75% synthetic)accuracy (%): 96.4 -> 95.2Hurt
sample difficulty with std 0.10 instead of fixed 0.00 (ablation)Difficulty score sampling · Imagenette (75% synthetic)accuracy (%): 95.8 -> 96.4Improved
raise difficulty std from 0.10 to 0.50 (ablation)Difficulty score sampling · Imagenette (75% synthetic)accuracy (%): 96.4 -> 96.0Hurt

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