Pubblicazioni

Autori:

Capogrosso, Luigi; Girella, Federico; Taioli, Francesco; Chiara, Michele; Aqeel, Muhammad; Fummi, Franco; Setti, Francesco; Cristani, Marco

Titolo:

Diffusion-Based Image Generation for In-Distribution Data Augmentation in Surface Defect Detection

Anno:

2024

Tipologia prodotto:

Contributo in atti di convegno

Tipologia ANVUR:

Contributo in Atti di convegno

Lingua:

Inglese

Formato:

Elettronico

Titolo del Convegno:

19th International Conference on Computer Vision Theory and Applications

Luogo:

Rome, Italy

Periodo:

27 - 29 February 2024

Casa editrice:

SciTePress

Intervallo pagine:

409-416

Parole chiave:

Diffusion Models, Data Augmentation, Surface Defect Detection

Breve descrizione dei contenuti:

In this study, we show that diffusion models can be used in industrial scenarios to improve the data augmentation procedure in the context of surface defect detection. In general, defect detection classifiers are trained on ground-truth data formed by normal samples (negative data) and samples with defects (positive data), where the latter are consistently fewer than normal samples. For these reasons, state-of-the-art data augmentation procedures add synthetic defect data by superimposing artifacts to normal samples. This leads to out-of-distribution augmented data so that the classification system learns what is not a normal sample but does not know what a defect really is. We show that diffusion models overcome this situation, providing more realistic in-distribution defects so that the model can learn the defect’s genuine appearance. We propose a novel approach for data augmentation that mixes out-of-distribution with in-distribution samples, which we call In&Out. The approach can deal with two data augmentation setups: i) when no defects are available (zero-shot data augmentation) and ii) when defects are available, which can be in a small number (few-shot) or a large one (full-shot). We focus the experimental part on the most challenging benchmark in the state-of-the-art, i.e., the Kolektor Surface-Defect Dataset 2, defining the new state-of-the-art classification AP score under weak supervision of .782. The code is available at https://github.com/intelligolabs/in_and_out.

Pagina Web:

https://www.scitepress.org/Link.aspx?doi=10.5220/0012350400003660

Id prodotto:

140000

Handle IRIS:

11562/1127946

ultima modifica:

5 giugno 2024

Citazione bibliografica:

Capogrosso, Luigi; Girella, Federico; Taioli, Francesco; Chiara, Michele; Aqeel, Muhammad; Fummi, Franco; Setti, Francesco; Cristani, Marco, Diffusion-Based Image Generation for In-Distribution Data Augmentation in Surface Defect Detection  in Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - (Volume 2) , SciTePress , Atti di "19th International Conference on Computer Vision Theory and Applications" , Rome, Italy , 27 - 29 February 2024 , 2024 , pp. 409-416

Consulta la scheda completa presente nel repository istituzionale della Ricerca di Ateneo