.png){kind=icon}
返回
ACKSNet: adaptive center keypoint selection for object detection
.png){kind=icon}
PRE
AI
DOI：10.1007/s00371-022-02712-x.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Keypoint-based detectors generate a large number of false positives due to incorrect keypoint matching in the object detection task. In this paper, we propose an adaptive center keypoint selection method (ACKSNet) to address the false-positive drawback. We first roughly group detected corners by associative embeddings, which flexibly localize objects of various shapes and scales to obtain a large number of initial candidate proposals. Then, ACKSNet associates introduced extra center keypoints with corner pairs through the geometric method to add location information in the candidate regions. And it independently generates a threshold for each center keypoint according to their statistical characteristics to ensure the high quality of center keypoints. Furthermore, we enrich the scale information of the output feature maps by equipping the backbone network with dilated convolution modules. On the MS COCO dataset, our model achieves an AP of 44.5%, surpassing most existing anchor-free detectors.
Keyword:
Keypoint-based
Object detection
Center keypoint
Adaptive
Scale information
期刊
IF:
2.9
论文数:
4.6K
被引数:
6.5K
机构
引用论文
The impact of temperature dependency of the building insulation thermal conductivity in the Canadian climate加拿大气候对建筑保温导热系数温度依赖性的影响
OAAI
OAAI分享收藏Conductivity Enhancement in Thin Silicon-on-Insulator Layer Embedding Artificial Dislocation Network
PREAI
分享收藏Excellent microwave absorption of Y2Fe15.5Co0.5Si/paraffin composites by tuning powder particle size
PREAI
分享收藏分享收藏Video object detection for autonomous driving: Motion-aid feature calibration.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容