A context-aware progressive attention aggregation network for fabric defect detection
Fabric defect detection plays a critical role for measuring quality control in the textile manufacturing industry. Deep learning-based saliency models can quickly spot the most interesting regions that attract human attention from the complex background, which have been successfully applied in fabri...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2023-06-01
|
| Series: | Journal of Engineered Fibers and Fabrics |
| Online Access: | https://doi.org/10.1177/15589250231174612 |
| _version_ | 1797810216382758912 |
|---|---|
| author | Zhoufeng Liu Bo Tian Chunlei Li Xiao Li Kaihua Wang |
| author_facet | Zhoufeng Liu Bo Tian Chunlei Li Xiao Li Kaihua Wang |
| author_sort | Zhoufeng Liu |
| collection | DOAJ |
| description | Fabric defect detection plays a critical role for measuring quality control in the textile manufacturing industry. Deep learning-based saliency models can quickly spot the most interesting regions that attract human attention from the complex background, which have been successfully applied in fabric defect detection. However, most of the previous methods mainly adopted multi-level feature aggregation yet ignored the complementary relationship among different features, and thus resulted in poor representation capability for the tiny and slender defects. To remedy these issues, we propose a novel saliency-based fabric defect detection network, which can exploit the complementary information between different layers to enhance the representation features ability and discrimination of defects. Specifically, a multi-scale feature aggregation unit (MFAU) is proposed to effectively characterize the multi-scale contextual features. Besides, a feature fusion refinement module (FFR) composed of an attention fusion unit (AFU) and an auxiliary refinement unit (ARU) is designed to exploit complementary important information and further refine the input features for enhancing the discriminative ability of defect features. Finally, a multi-level deep supervision (MDS) is adopted to guide the model to generate more accurate saliency maps. Under different evaluation metrics, our proposed method outperforms most state-of-the-art methods on our developed fabric datasets. |
| first_indexed | 2024-03-13T07:04:48Z |
| format | Article |
| id | doaj.art-ca3025c7de1c4da181f05c4eb524e3a6 |
| institution | Directory Open Access Journal |
| issn | 1558-9250 |
| language | English |
| last_indexed | 2024-03-13T07:04:48Z |
| publishDate | 2023-06-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Journal of Engineered Fibers and Fabrics |
| spelling | doaj.art-ca3025c7de1c4da181f05c4eb524e3a62023-06-06T13:04:46ZengSAGE PublishingJournal of Engineered Fibers and Fabrics1558-92502023-06-011810.1177/15589250231174612A context-aware progressive attention aggregation network for fabric defect detectionZhoufeng LiuBo TianChunlei LiXiao LiKaihua WangFabric defect detection plays a critical role for measuring quality control in the textile manufacturing industry. Deep learning-based saliency models can quickly spot the most interesting regions that attract human attention from the complex background, which have been successfully applied in fabric defect detection. However, most of the previous methods mainly adopted multi-level feature aggregation yet ignored the complementary relationship among different features, and thus resulted in poor representation capability for the tiny and slender defects. To remedy these issues, we propose a novel saliency-based fabric defect detection network, which can exploit the complementary information between different layers to enhance the representation features ability and discrimination of defects. Specifically, a multi-scale feature aggregation unit (MFAU) is proposed to effectively characterize the multi-scale contextual features. Besides, a feature fusion refinement module (FFR) composed of an attention fusion unit (AFU) and an auxiliary refinement unit (ARU) is designed to exploit complementary important information and further refine the input features for enhancing the discriminative ability of defect features. Finally, a multi-level deep supervision (MDS) is adopted to guide the model to generate more accurate saliency maps. Under different evaluation metrics, our proposed method outperforms most state-of-the-art methods on our developed fabric datasets.https://doi.org/10.1177/15589250231174612 |
| spellingShingle | Zhoufeng Liu Bo Tian Chunlei Li Xiao Li Kaihua Wang A context-aware progressive attention aggregation network for fabric defect detection Journal of Engineered Fibers and Fabrics |
| title | A context-aware progressive attention aggregation network for fabric defect detection |
| title_full | A context-aware progressive attention aggregation network for fabric defect detection |
| title_fullStr | A context-aware progressive attention aggregation network for fabric defect detection |
| title_full_unstemmed | A context-aware progressive attention aggregation network for fabric defect detection |
| title_short | A context-aware progressive attention aggregation network for fabric defect detection |
| title_sort | context aware progressive attention aggregation network for fabric defect detection |
| url | https://doi.org/10.1177/15589250231174612 |
| work_keys_str_mv | AT zhoufengliu acontextawareprogressiveattentionaggregationnetworkforfabricdefectdetection AT botian acontextawareprogressiveattentionaggregationnetworkforfabricdefectdetection AT chunleili acontextawareprogressiveattentionaggregationnetworkforfabricdefectdetection AT xiaoli acontextawareprogressiveattentionaggregationnetworkforfabricdefectdetection AT kaihuawang acontextawareprogressiveattentionaggregationnetworkforfabricdefectdetection AT zhoufengliu contextawareprogressiveattentionaggregationnetworkforfabricdefectdetection AT botian contextawareprogressiveattentionaggregationnetworkforfabricdefectdetection AT chunleili contextawareprogressiveattentionaggregationnetworkforfabricdefectdetection AT xiaoli contextawareprogressiveattentionaggregationnetworkforfabricdefectdetection AT kaihuawang contextawareprogressiveattentionaggregationnetworkforfabricdefectdetection |