Transcription of CenterNet: Keypoint Triplets for Object Detection
{{id}} {{{paragraph}}}
Example: bankruptcy
CenterNet: Keypoint Triplets for Object Detection
CenterNet: Keypoint Triplets for Object DetectionKaiwen Duan1 Song Bai2 Lingxi Xie3 Honggang Qi1,4 Qingming Huang1,4,5 Qi Tian3 1 University of Chinese Academy of Sciences2 Huazhong University of Science and Technology3 Huawei Noah s Ark Lab4 Key Laboratory of Big Data Mining and Knowledge Management, UCAS5 Peng Cheng Object Detection , Keypoint -based approaches often ex-perience the drawback of a large number of incorrect objectbounding boxes, arguably due to the lack of an additionalassessment inside cropped regions. This paper presents anefficient solution that explores the visual patterns within in-dividual cropped regions with minimal costs. We build ourframework upon a representative one-stage Keypoint -baseddetector named CornerNet. Our approach, named Center-Net, detects each Object as a triplet, rather than a pair, ofkeypoints, which improves both precision and recall.
Table 1: False discovery rates (%) of CornerNet. The false discovery rate reflects the distribution of incorrect bound-ing boxes. The results suggest that the incorrect bounding boxes account for a large proportion of all bounding boxes. heatmap of the top-left corners and a heatmap of the bottom-right corners. The heatmaps represent the locations
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: