MED-AGNeT: An attention-guided network of customized augmentation of samples based on conditional diffusion for textile defect detection
Fabric defect detection plays a vital role in ensuring the production quality of the textile manufacturing industry. However, in practice, there are relatively few manually annotated defective samples, and considering both performance and parameter quantity, there is still room for optimization in t...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2025-12-01
|
| Series: | International Journal of Cognitive Computing in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666307425000026 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595843571515392 |
|---|---|
| author | Jun Liu Haolin Li Hao Liu Jiuzhen Liang |
| author_facet | Jun Liu Haolin Li Hao Liu Jiuzhen Liang |
| author_sort | Jun Liu |
| collection | DOAJ |
| description | Fabric defect detection plays a vital role in ensuring the production quality of the textile manufacturing industry. However, in practice, there are relatively few manually annotated defective samples, and considering both performance and parameter quantity, there is still room for optimization in the architecture of detection networks. Therefore, this paper proposes a textile defect detection method called MED-AGNet. Firstly, based on the diffusion model, a mask-embedding data augmentation method, MEDiffusion, is proposed. During the training process, a conditional term (M) that represents the shape of the defect is added, and through supervised learning, the generative model learns the correlation between the background and defects. In the generation stage, it samples from a normal distribution and relies on M guidance to gradually generate corresponding defective textiles, thereby expanding the original sample set. An attention-guided network (AGNet) is a network that utilizes attention to guide information across different scales. Its feature extraction module employs a dual-branch information residual unit (DIRU) as a substitute for the conventional convolution block, which combines the feature extraction capabilities of global pooling and max pooling, reducing the number of parameters while also achieving a certain improvement in detection results. In the feature fusion stage, it utilizes the attention-guided fusion module (AGFM), which can allow the attention information of high-level semantics to guide the low-level semantics, and simultaneously, adds a high-level semantic residual attention module (HSRA) to enhance the perception of defect shapes and improve detection effectiveness. Ultimately, AGNet’s true positive rate (TPR), positive predictive value (PPV), and f-measure exceed those of the state-of-the-art (SOTA) algorithms by 1.88%, 0.05%, and 0.77%, respectively, and with a consistent model architecture, its parameter quantity is reduced by 56%. |
| format | Article |
| id | doaj-art-e9516ee1ee0c4bcbb011a99e5a21163b |
| institution | Kabale University |
| issn | 2666-3074 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | International Journal of Cognitive Computing in Engineering |
| spelling | doaj-art-e9516ee1ee0c4bcbb011a99e5a21163b2025-01-18T05:05:15ZengKeAi Communications Co., Ltd.International Journal of Cognitive Computing in Engineering2666-30742025-12-016238254MED-AGNeT: An attention-guided network of customized augmentation of samples based on conditional diffusion for textile defect detectionJun Liu0Haolin Li1Hao Liu2Jiuzhen Liang3Changzhou University, Changzhou, 213164, ChinaCorresponding author.; Changzhou University, Changzhou, 213164, ChinaChangzhou University, Changzhou, 213164, ChinaChangzhou University, Changzhou, 213164, ChinaFabric defect detection plays a vital role in ensuring the production quality of the textile manufacturing industry. However, in practice, there are relatively few manually annotated defective samples, and considering both performance and parameter quantity, there is still room for optimization in the architecture of detection networks. Therefore, this paper proposes a textile defect detection method called MED-AGNet. Firstly, based on the diffusion model, a mask-embedding data augmentation method, MEDiffusion, is proposed. During the training process, a conditional term (M) that represents the shape of the defect is added, and through supervised learning, the generative model learns the correlation between the background and defects. In the generation stage, it samples from a normal distribution and relies on M guidance to gradually generate corresponding defective textiles, thereby expanding the original sample set. An attention-guided network (AGNet) is a network that utilizes attention to guide information across different scales. Its feature extraction module employs a dual-branch information residual unit (DIRU) as a substitute for the conventional convolution block, which combines the feature extraction capabilities of global pooling and max pooling, reducing the number of parameters while also achieving a certain improvement in detection results. In the feature fusion stage, it utilizes the attention-guided fusion module (AGFM), which can allow the attention information of high-level semantics to guide the low-level semantics, and simultaneously, adds a high-level semantic residual attention module (HSRA) to enhance the perception of defect shapes and improve detection effectiveness. Ultimately, AGNet’s true positive rate (TPR), positive predictive value (PPV), and f-measure exceed those of the state-of-the-art (SOTA) algorithms by 1.88%, 0.05%, and 0.77%, respectively, and with a consistent model architecture, its parameter quantity is reduced by 56%.http://www.sciencedirect.com/science/article/pii/S2666307425000026Diffusion with mask conditionFabric data augmentationAttention-guided feature fusionFabric defect detection |
| spellingShingle | Jun Liu Haolin Li Hao Liu Jiuzhen Liang MED-AGNeT: An attention-guided network of customized augmentation of samples based on conditional diffusion for textile defect detection International Journal of Cognitive Computing in Engineering Diffusion with mask condition Fabric data augmentation Attention-guided feature fusion Fabric defect detection |
| title | MED-AGNeT: An attention-guided network of customized augmentation of samples based on conditional diffusion for textile defect detection |
| title_full | MED-AGNeT: An attention-guided network of customized augmentation of samples based on conditional diffusion for textile defect detection |
| title_fullStr | MED-AGNeT: An attention-guided network of customized augmentation of samples based on conditional diffusion for textile defect detection |
| title_full_unstemmed | MED-AGNeT: An attention-guided network of customized augmentation of samples based on conditional diffusion for textile defect detection |
| title_short | MED-AGNeT: An attention-guided network of customized augmentation of samples based on conditional diffusion for textile defect detection |
| title_sort | med agnet an attention guided network of customized augmentation of samples based on conditional diffusion for textile defect detection |
| topic | Diffusion with mask condition Fabric data augmentation Attention-guided feature fusion Fabric defect detection |
| url | http://www.sciencedirect.com/science/article/pii/S2666307425000026 |
| work_keys_str_mv | AT junliu medagnetanattentionguidednetworkofcustomizedaugmentationofsamplesbasedonconditionaldiffusionfortextiledefectdetection AT haolinli medagnetanattentionguidednetworkofcustomizedaugmentationofsamplesbasedonconditionaldiffusionfortextiledefectdetection AT haoliu medagnetanattentionguidednetworkofcustomizedaugmentationofsamplesbasedonconditionaldiffusionfortextiledefectdetection AT jiuzhenliang medagnetanattentionguidednetworkofcustomizedaugmentationofsamplesbasedonconditionaldiffusionfortextiledefectdetection |