Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2412.14379 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908446959337472 |
|---|---|
| author | Nguyen, Phuc D. A. |
| author_facet | Nguyen, Phuc D. A. |
| contents | Oriented object detection in aerial images poses a significant challenge due to their varying sizes and orientations. Current state-of-the-art detectors typically rely on either two-stage or one-stage approaches, often employing Anchor-based strategies, which can result in computationally expensive operations due to the redundant number of generated anchors during training. In contrast, Anchor-free mechanisms offer faster processing but suffer from a reduction in the number of training samples, potentially impacting detection accuracy. To address these limitations, we propose the Hybrid-Anchor Rotation Detector (HA-RDet), which combines the advantages of both anchor-based and anchor-free schemes for oriented object detection. By utilizing only one preset anchor for each location on the feature maps and refining these anchors with our Orientation-Aware Convolution technique, HA-RDet achieves competitive accuracies, including 75.41 mAP on DOTA-v1, 65.3 mAP on DIOR-R, and 90.2 mAP on HRSC2016, against current anchor-based state-of-the-art methods, while significantly reducing computational resources. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_14379 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HA-RDet: Hybrid Anchor Rotation Detector for Oriented Object Detection Nguyen, Phuc D. A. Computer Vision and Pattern Recognition Oriented object detection in aerial images poses a significant challenge due to their varying sizes and orientations. Current state-of-the-art detectors typically rely on either two-stage or one-stage approaches, often employing Anchor-based strategies, which can result in computationally expensive operations due to the redundant number of generated anchors during training. In contrast, Anchor-free mechanisms offer faster processing but suffer from a reduction in the number of training samples, potentially impacting detection accuracy. To address these limitations, we propose the Hybrid-Anchor Rotation Detector (HA-RDet), which combines the advantages of both anchor-based and anchor-free schemes for oriented object detection. By utilizing only one preset anchor for each location on the feature maps and refining these anchors with our Orientation-Aware Convolution technique, HA-RDet achieves competitive accuracies, including 75.41 mAP on DOTA-v1, 65.3 mAP on DIOR-R, and 90.2 mAP on HRSC2016, against current anchor-based state-of-the-art methods, while significantly reducing computational resources. |
| title | HA-RDet: Hybrid Anchor Rotation Detector for Oriented Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.14379 |