A fully automatic pipeline generates synthetic industrial defects with VLM prompts, LoRA diffusion, and auto-labeling; adding these to real data gives modest AP gains only in selected configurations.
Do we need all the synthetic data? targeted synthetic image augmentation via diffusion models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SynSur: An end-to-end generative pipeline for synthetic industrial surface defect generation and detection
A fully automatic pipeline generates synthetic industrial defects with VLM prompts, LoRA diffusion, and auto-labeling; adding these to real data gives modest AP gains only in selected configurations.