Physical World & Real-World ImpactChemnitz University of Technology, Voxar Labs (UFPE)
Study on GAN augmentation for wafer dicing defects
Study on GAN augmentation for wafer dicing defects — 6 defect classes; the test set uses real images only, excluding synthetic ones. By the authors' measurement, balanced accuracy rose from 65.1% to 88.2% with DCGAN augmentation
Why it matters
Dicing is the first step of back-end processing. A 23-percentage-point gain from synthetic augmentation alone on a small set of defect images speaks directly to the early data-scarce phase of new defect classes
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2407.20268Added in Week 35, 2026 · See that week