AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Few-shot Defect Image Generation based on Consistency Modeling

Qingfeng Shi, Jing Wei, Fei Shen, Zhengtao Zhang

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 17 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 the fusion part to the generation module (ablation)DefectDiffu · MVTecAD averageFID: 149.83 -> 69.35Improved
add adaptive attention-enhanced loss (AAL) (ablation)DefectDiffu · MVTecAD averageFID: 152.77 -> 69.35Improved
use multiple single-object text prompts instead of one fused prompt (ablation)DefectDiffu · MVTecAD averageFID: 197.55 -> 69.35Improved
generate at multiple defect strength scales w_d instead of single scale (ablation)DefectDiffu · MVTecAD averageLPIPS: 0.20 -> 0.21Improved
augment segmentation training with DefectDiffu synthetic image-mask pairsUNet · MVTecAD averagemIoU: 60.3 -> 67.1Improved
augment segmentation training with DFMGAN synthetic dataUNet · MVTecAD averagemIoU: 60.3 -> 60.3No clear effect
augment segmentation training with Defect-Gen synthetic dataUNet · MVTecAD averagemIoU: 60.3 -> 63.5Improved
use DefectDiffu instead of Defect-Gen for diversityDefectDiffu · MVTecAD averageLPIPS: 0.24 -> 0.21Hurt

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