%0 Generic %1 duan2019centernet %A Duan, Kaiwen %A Bai, Song %A Xie, Lingxi %A Qi, Honggang %A Huang, Qingming %A Tian, Qi %D 2019 %K %T CenterNet: Keypoint Triplets for Object Detection %U http://arxiv.org/abs/1904.08189 %X In object detection, keypoint-based approaches often suffer a large number of incorrect object bounding boxes, arguably due to the lack of an additional look into the cropped regions. This paper presents an efficient solution which explores the visual patterns within each cropped region with minimal costs. We build our framework upon a representative one-stage keypoint-based detector named CornerNet. Our approach, named CenterNet, detects each object as a triplet, rather than a pair, of keypoints, which improves both precision and recall. Accordingly, we design two customized modules named cascade corner pooling and center pooling, which play the roles of enriching information collected by both top-left and bottom-right corners and providing more recognizable information at the central regions, respectively. On the MS-COCO dataset, CenterNet achieves an AP of 47.0%, which outperforms all existing one-stage detectors by at least 4.9%. Meanwhile, with a faster inference speed, CenterNet demonstrates quite comparable performance to the top-ranked two-stage detectors. Code is available at https://github.com/Duankaiwen/CenterNet.

@misc{duan2019centernet, abstract = {In object detection, keypoint-based approaches often suffer a large number of incorrect object bounding boxes, arguably due to the lack of an additional look into the cropped regions. This paper presents an efficient solution which explores the visual patterns within each cropped region with minimal costs. We build our framework upon a representative one-stage keypoint-based detector named CornerNet. Our approach, named CenterNet, detects each object as a triplet, rather than a pair, of keypoints, which improves both precision and recall. Accordingly, we design two customized modules named cascade corner pooling and center pooling, which play the roles of enriching information collected by both top-left and bottom-right corners and providing more recognizable information at the central regions, respectively. On the MS-COCO dataset, CenterNet achieves an AP of 47.0%, which outperforms all existing one-stage detectors by at least 4.9%. Meanwhile, with a faster inference speed, CenterNet demonstrates quite comparable performance to the top-ranked two-stage detectors. Code is available at https://github.com/Duankaiwen/CenterNet.}, added-at = {2019-05-09T08:53:09.000+0200}, author = {Duan, Kaiwen and Bai, Song and Xie, Lingxi and Qi, Honggang and Huang, Qingming and Tian, Qi}, biburl = {https://www.bibsonomy.org/bibtex/2eaf9e599e276b3e3de777f244d1c3c29/nmatsuk}, interhash = {2359a980f5b70d2c19c87a248160cb4b}, intrahash = {eaf9e599e276b3e3de777f244d1c3c29}, keywords = {}, note = {cite arxiv:1904.08189Comment: 10 pages (including 2 pages of References), 7 figures, 5 tables}, timestamp = {2019-05-09T08:53:09.000+0200}, title = {CenterNet: Keypoint Triplets for Object Detection}, url = {http://arxiv.org/abs/1904.08189}, year = 2019 }