A contrastive learning-based attention generative adversarial network for defect detection in colour-patterned fabric in COLORATION TECHNOLOGY, Vol. 139, N° 3 (06/2023)  

[article]  inCOLORATION TECHNOLOGY > Vol. 139, N° 3 (06/2023) . - p. 248-264 Titre : A contrastive learning-based attention generative adversarial network for defect detection in colour-patterned fabric Type de document : texte imprimé Année de publication : 2023 Article en page(s) : p. 248-264 Note générale : Bibliogr. Langues : Anglais (eng) Catégories : Apprentissage contrastif Détection de défauts (Ingénierie) Textiles et tissus -- Défauts Textiles et tissus teints Index. décimale : 667.3 Teinture et impression des tissus Résumé : The pattern style of colour-patterned fabrics is varied. Defective fabric samples are scarce in the production of small batches of colour-patterned fabrics. Therefore, the unsupervised defect-detection method for colour-patterned fabric has attracted wide attention. Several unsupervised defect-detection methods for colour-patterned fabrics based on convolutional neural networks have been proposed. However, convolutional neural network methods cannot learn long-range semantic information interaction well because of the intrinsic locality of convolution operations. Besides, as the number of layers in the convolutional neural network increases, the feature maps become more and more complex. Convolutional neural networks experience difficulties in coordinating numerous parameters and extracting key features from complex feature maps. Both these problems reduce the accuracy of the model for detecting defects in colour-patterned fabrics. In this paper, we propose a Contrastive Learning-based Attention Generative Adversarial Network (CLAGAN) for defect detection in colour-patterned fabrics. The CLAGAN possesses two important parts: contrastive learning and a channel attention module. Contrastive learning captures long-range dependencies by calculating the cosine similarity between different features. The channel attention module assigns different weights to each channel of the feature maps, and it enables the model to extract key features from those feature maps. The experimental results verified the effectiveness of the CLAGAN. It obtained values of 38.25% for intersection over union and of 51.67% for the F1-measure on the YDFID-2 public dataset. Note de contenu : - RELATED WORKS : Fabric defect-detection methods based on deep learning - Contrastive learning - Attention mechanism - THE PROPOSED CLAGAN MODEL : An overview of the CLAGAN - Defect detection in colour-patterned fabric based on the CLAGAN - RESULTS AND DISCUSSION : Datasets - Evaluation metric - Implementation detail - Experimental results and analysis - Table 1 : The number of colour-patterned fabric samples - Table 2 : Quantitative detection results for different methods on the YDFID-1 dataset - Table 3 : Quantitative detection results for different methods on the ZJU-Leaper dataset - Table 4 : Experimental results for the noise fraction - Table 5 : Experimental results for the ablation study DOI : https://doi.org/10.1111/cote.12642 En ligne : https://onlinelibrary.wiley.com/doi/epdf/10.1111/cote.12642 Format de la ressource électronique : Pdf Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=39536 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
24086	-	Périodique	Bibliothèque principale	Documentaires	Disponible

---

1 (1 - 1 / 1)