AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Defect Spectrum: A Granular Look of Large-scale Defect Datasets with Rich Semantics

Shuai Yang, ZhiFei Chen, Pengguang Chen, Xi Fang, Yixun Liang, Shu Liu, Yingcong Chen

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection · 21 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 Defect-Gen synthetic training dataMiT-B0 · DS-MVTecmIoU: 46.45 -> 56.21Improved
add Defect-Gen synthetic training dataDeepLabV3+ · DS-CottonmIoU: 48.73 -> 58.58Improved
add Defect-Gen synthetic training dataDeepLabV3+ · DS-VISIONmIoU: 52.33 -> 53.46Improved
add Defect-Gen synthetic data to Mask2FormerMask2Former · DS-CottonmIoU: 64.09 -> 65.39Improved
use synthetic data equal to 100% of the training set rather than more (ablation)DeepLabV3+ / MiT-B0 · Defect Spectrum (MVTec)mIoUMixed
train on Defect Spectrum refined annotations instead of original annotationssegmentation model · MVTec simulated productionfalse positive rate (%): 49.60 -> 16.50Improved
train on Defect Spectrum refined annotations instead of original annotationssegmentation model · MVTec simulated productionrecall (%): 85.33 -> 96.07Improved
augment with sinDiffusion-generated imagessegmentation model · Original MVTec (mean)mIoU: 64.01 -> 63.51Hurt
augment with DDPM-generated imagessegmentation model · Original MVTec (mean)mIoU: 64.01 -> 65.07Improved
augment with Defect-Gen imagessegmentation model · Original MVTec (mean)mIoU: 64.01 -> 67.76Improved
increase the DDPM-style switch timestep u from 25 to 700 (ablation)Defect-Gen (small receptive field) · capsule class (generation)FID: 115.2754 -> 78.4115Improved
use a larger receptive field in the small model (ablation)Defect-Gen · capsule class (generation)LPIPS: 0.3666 -> 0.2870 at u=50 (small to large); FID 93.2839 -> 56.6246Mixed

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