FDDNet: Fabric defect detection with spatial depth-transforming convolution and multiscale dilated self-attention fusion module

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Fabric defect detection shows improved localization in textiles, suggesting deep learning methods enhance accuracy.

FDDNet improved fabric defect detection's accuracy addressing local and global feature limitations.
Key evidence indicates an AP50 score of 56.8% on the denim dataset, outperforming existing methods.
The study employs a novel approach using convolutional neural networks, integrating various advanced techniques.
Deep learning advancements may enhance inspection processes in textile manufacturing, potentially reducing waste.

Huang et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

Fabric defect detection shows improved localization in textiles, suggesting deep learning methods enhance accuracy.

FDDNet improved fabric defect detection's accuracy addressing local and global feature limitations.
Key evidence indicates an AP50 score of 56.8% on the denim dataset, outperforming existing methods.
The study employs a novel approach using convolutional neural networks, integrating various advanced techniques.
Deep learning advancements may enhance inspection processes in textile manufacturing, potentially reducing waste.

Huang et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark