DefFiller: Mask-Conditioned Diffusion for Salient Steel Surface Defect Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916535444963328 |
|---|---|
| author | Tai, Yichun Huang, Zhenzhen Peng, Tao Zhang, Zhijiang |
| author_facet | Tai, Yichun Huang, Zhenzhen Peng, Tao Zhang, Zhijiang |
| contents | Current saliency-based defect detection methods show promise in industrial settings, but the unpredictability of defects in steel production environments complicates dataset creation, hampering model performance. Existing data augmentation approaches using generative models often require pixel-level annotations, which are time-consuming and resource-intensive. To address this, we introduce DefFiller, a mask-conditioned defect generation method that leverages a layout-to-image diffusion model. DefFiller generates defect samples paired with mask conditions, eliminating the need for pixel-level annotations and enabling direct use in model training. We also develop an evaluation framework to assess the quality of generated samples and their impact on detection performance. Experimental results on the SD-Saliency-900 dataset demonstrate that DefFiller produces high-quality defect images that accurately match the provided mask conditions, significantly enhancing the performance of saliency-based defect detection models trained on the augmented dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_15570 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DefFiller: Mask-Conditioned Diffusion for Salient Steel Surface Defect Generation Tai, Yichun Huang, Zhenzhen Peng, Tao Zhang, Zhijiang Computer Vision and Pattern Recognition Current saliency-based defect detection methods show promise in industrial settings, but the unpredictability of defects in steel production environments complicates dataset creation, hampering model performance. Existing data augmentation approaches using generative models often require pixel-level annotations, which are time-consuming and resource-intensive. To address this, we introduce DefFiller, a mask-conditioned defect generation method that leverages a layout-to-image diffusion model. DefFiller generates defect samples paired with mask conditions, eliminating the need for pixel-level annotations and enabling direct use in model training. We also develop an evaluation framework to assess the quality of generated samples and their impact on detection performance. Experimental results on the SD-Saliency-900 dataset demonstrate that DefFiller produces high-quality defect images that accurately match the provided mask conditions, significantly enhancing the performance of saliency-based defect detection models trained on the augmented dataset. |
| title | DefFiller: Mask-Conditioned Diffusion for Salient Steel Surface Defect Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.15570 |