Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2604.22850 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914506065575936 |
|---|---|
| author | Güğül, Serkan Hamdi Levi, Kemal Acar, Burak |
| author_facet | Güğül, Serkan Hamdi Levi, Kemal Acar, Burak |
| contents | Industrial visual inspection systems often suffer from a severe scarcity of labeled defect data, particularly during the early stages of New Product Introduction (NPI). This limitation hinders the deployment of robust supervised detectors precisely when automated quality control is most needed. We present an end-to-end generative framework for high-fidelity, few-shot defect synthesis that enables both in-domain augmentation and cross-domain transfer. Our approach disentangles defect morphology from background appearance by combining masked textual inversion for defect representation learning, noise-blended conditioned generation for surface-aware synthesis, and gradient-aware post-processing for seamless visual integration. We evaluate the framework in two practically relevant settings: few-shot data augmentation, where synthetic samples enrich a small set of real defects, and zero-shot adaptation, where defects learned from a source domain are transferred to a novel target surface without any real target-domain defect examples. Using RF-DETR as the downstream detector, we show that the proposed pipeline substantially narrows the domain gap on a private industrial dataset. In the few-shot setting, synthetic augmentation improves mAP from 78.8% to 83.3%. In the zero-shot setting, synthetic domain adaptation improves mAP from 65.0% to 85.1%. These results demonstrate that high-fidelity defect synthesis can meaningfully accelerate NPI by enabling effective inspection models before sufficient real defect data has been collected. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_22850 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Accelerating New Product Introduction for Visual Quality Inspection via Few-Shot Diffusion-Based Defect Synthesis Güğül, Serkan Hamdi Levi, Kemal Acar, Burak Computer Vision and Pattern Recognition Machine Learning Industrial visual inspection systems often suffer from a severe scarcity of labeled defect data, particularly during the early stages of New Product Introduction (NPI). This limitation hinders the deployment of robust supervised detectors precisely when automated quality control is most needed. We present an end-to-end generative framework for high-fidelity, few-shot defect synthesis that enables both in-domain augmentation and cross-domain transfer. Our approach disentangles defect morphology from background appearance by combining masked textual inversion for defect representation learning, noise-blended conditioned generation for surface-aware synthesis, and gradient-aware post-processing for seamless visual integration. We evaluate the framework in two practically relevant settings: few-shot data augmentation, where synthetic samples enrich a small set of real defects, and zero-shot adaptation, where defects learned from a source domain are transferred to a novel target surface without any real target-domain defect examples. Using RF-DETR as the downstream detector, we show that the proposed pipeline substantially narrows the domain gap on a private industrial dataset. In the few-shot setting, synthetic augmentation improves mAP from 78.8% to 83.3%. In the zero-shot setting, synthetic domain adaptation improves mAP from 65.0% to 85.1%. These results demonstrate that high-fidelity defect synthesis can meaningfully accelerate NPI by enabling effective inspection models before sufficient real defect data has been collected. |
| title | Accelerating New Product Introduction for Visual Quality Inspection via Few-Shot Diffusion-Based Defect Synthesis |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2604.22850 |