Mirror-Yolo: A Novel Attention Focus, Instance Segmentation and Mirror Detection Model
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916467586367488 |
|---|---|
| author | Li, Fengze Ma, Jieming Tian, Zhongbei Ge, Ji Liang, Hai-Ning Zhang, Yungang Wen, Tianxi |
| author_facet | Li, Fengze Ma, Jieming Tian, Zhongbei Ge, Ji Liang, Hai-Ning Zhang, Yungang Wen, Tianxi |
| contents | Mirrors can degrade the performance of computer vision models, but research into detecting them is in the preliminary phase. YOLOv4 achieves phenomenal results in terms of object detection accuracy and speed, but it still fails in detecting mirrors. Thus, we propose Mirror-YOLO, which targets mirror detection, containing a novel attention focus mechanism for features acquisition, a hypercolumn-stairstep approach to better fusion the feature maps, and the mirror bounding polygons for instance segmentation. Compared to the existing mirror detection networks and YOLO series, our proposed network achieves superior performance in average accuracy on our proposed mirror dataset and another state-of-art mirror dataset, which demonstrates the validity and effectiveness of Mirror-YOLO. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2202_08498 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Mirror-Yolo: A Novel Attention Focus, Instance Segmentation and Mirror Detection Model Li, Fengze Ma, Jieming Tian, Zhongbei Ge, Ji Liang, Hai-Ning Zhang, Yungang Wen, Tianxi Computer Vision and Pattern Recognition Mirrors can degrade the performance of computer vision models, but research into detecting them is in the preliminary phase. YOLOv4 achieves phenomenal results in terms of object detection accuracy and speed, but it still fails in detecting mirrors. Thus, we propose Mirror-YOLO, which targets mirror detection, containing a novel attention focus mechanism for features acquisition, a hypercolumn-stairstep approach to better fusion the feature maps, and the mirror bounding polygons for instance segmentation. Compared to the existing mirror detection networks and YOLO series, our proposed network achieves superior performance in average accuracy on our proposed mirror dataset and another state-of-art mirror dataset, which demonstrates the validity and effectiveness of Mirror-YOLO. |
| title | Mirror-Yolo: A Novel Attention Focus, Instance Segmentation and Mirror Detection Model |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2202.08498 |