Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.00589 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916377201213440 |
|---|---|
| author | Liu, Biyuan Chen, Huaixin Zhan, Huiyao Luo, Sijie Huang, Zhou |
| author_facet | Liu, Biyuan Chen, Huaixin Zhan, Huiyao Luo, Sijie Huang, Zhou |
| contents | Despite the eye-catching breakthroughs achieved by deep visual networks in detecting region-level surface defects, the challenge of high-quality pixel-wise defect detection remains due to diverse defect appearances and data scarcity. To avoid over-reliance on defect appearance and achieve accurate defect segmentation, we proposed a change-aware Siamese network that solves the defect segmentation in a change detection framework. A novel multi-class balanced contrastive loss is introduced to guide the Transformer-based encoder, which enables encoding diverse categories of defects as the unified class-agnostic difference between defect and defect-free images. The difference presented by a distance map is then skip-connected to the change-aware decoder to assist in the location of both inter-class and out-of-class pixel-wise defects. In addition, we proposed a synthetic dataset with multi-class liquid crystal display (LCD) defects under a complex and disjointed background context, to demonstrate the advantages of change-based modeling over appearance-based modeling for defect segmentation. In our proposed dataset and two public datasets, our model achieves superior performances than the leading semantic segmentation methods, while maintaining a relatively small model size. Moreover, our model achieves a new state-of-the-art performance compared to the semi-supervised approaches in various supervision settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_00589 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Change-Aware Siamese Network for Surface Defects Segmentation under Complex Background Liu, Biyuan Chen, Huaixin Zhan, Huiyao Luo, Sijie Huang, Zhou Computer Vision and Pattern Recognition Despite the eye-catching breakthroughs achieved by deep visual networks in detecting region-level surface defects, the challenge of high-quality pixel-wise defect detection remains due to diverse defect appearances and data scarcity. To avoid over-reliance on defect appearance and achieve accurate defect segmentation, we proposed a change-aware Siamese network that solves the defect segmentation in a change detection framework. A novel multi-class balanced contrastive loss is introduced to guide the Transformer-based encoder, which enables encoding diverse categories of defects as the unified class-agnostic difference between defect and defect-free images. The difference presented by a distance map is then skip-connected to the change-aware decoder to assist in the location of both inter-class and out-of-class pixel-wise defects. In addition, we proposed a synthetic dataset with multi-class liquid crystal display (LCD) defects under a complex and disjointed background context, to demonstrate the advantages of change-based modeling over appearance-based modeling for defect segmentation. In our proposed dataset and two public datasets, our model achieves superior performances than the leading semantic segmentation methods, while maintaining a relatively small model size. Moreover, our model achieves a new state-of-the-art performance compared to the semi-supervised approaches in various supervision settings. |
| title | Change-Aware Siamese Network for Surface Defects Segmentation under Complex Background |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.00589 |