Controllable Image Synthesis of Industrial Data Using Stable Diffusion
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916081889705984 |
|---|---|
| author | Valvano, Gabriele Agostino, Antonino De Magistris, Giovanni Graziano, Antonino Veneri, Giacomo |
| author_facet | Valvano, Gabriele Agostino, Antonino De Magistris, Giovanni Graziano, Antonino Veneri, Giacomo |
| contents | Training supervised deep neural networks that perform defect detection and segmentation requires large-scale fully-annotated datasets, which can be hard or even impossible to obtain in industrial environments. Generative AI offers opportunities to enlarge small industrial datasets artificially, thus enabling the usage of state-of-the-art supervised approaches in the industry. Unfortunately, also good generative models need a lot of data to train, while industrial datasets are often tiny. Here, we propose a new approach for reusing general-purpose pre-trained generative models on industrial data, ultimately allowing the generation of self-labelled defective images. First, we let the model learn the new concept, entailing the novel data distribution. Then, we force it to learn to condition the generative process, producing industrial images that satisfy well-defined topological characteristics and show defects with a given geometry and location. To highlight the advantage of our approach, we use the synthetic dataset to optimise a crack segmentor for a real industrial use case. When the available data is small, we observe considerable performance increase under several metrics, showing the method's potential in production environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_03152 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Controllable Image Synthesis of Industrial Data Using Stable Diffusion Valvano, Gabriele Agostino, Antonino De Magistris, Giovanni Graziano, Antonino Veneri, Giacomo Computer Vision and Pattern Recognition Machine Learning Training supervised deep neural networks that perform defect detection and segmentation requires large-scale fully-annotated datasets, which can be hard or even impossible to obtain in industrial environments. Generative AI offers opportunities to enlarge small industrial datasets artificially, thus enabling the usage of state-of-the-art supervised approaches in the industry. Unfortunately, also good generative models need a lot of data to train, while industrial datasets are often tiny. Here, we propose a new approach for reusing general-purpose pre-trained generative models on industrial data, ultimately allowing the generation of self-labelled defective images. First, we let the model learn the new concept, entailing the novel data distribution. Then, we force it to learn to condition the generative process, producing industrial images that satisfy well-defined topological characteristics and show defects with a given geometry and location. To highlight the advantage of our approach, we use the synthetic dataset to optimise a crack segmentor for a real industrial use case. When the available data is small, we observe considerable performance increase under several metrics, showing the method's potential in production environments. |
| title | Controllable Image Synthesis of Industrial Data Using Stable Diffusion |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2401.03152 |